© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3339
    Prev
    Next
    INDEX
    Explanations

    terms related to employment and workplace policies.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms related to legal documents or human resources policies.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to individuals having or performing actions, often in a professional or organizational context. It seems to activate strongly for constructions like "[person/role] has/will/can [action]" or descriptions of what a person or role is able or expected to do.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Possessive pronouns (his, her, their)

    np_acts-logits-general · gemini-2.0-flash

    his or her

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.72
    Parcelize
    -0.72
     grandsons
    -0.66
     Inflate
    -0.64
    AndEndTag
    -0.61
     Roskov
    -0.61
     Guys
    -0.60
    guys
    -0.60
     guys
    -0.60
     invokingState
    -0.59
    POSITIVE LOGITS
     their
    1.12
    Their
    1.03
    their
    0.97
     Their
    0.97
     himself
    0.94
     herself
    0.94
     THEIR
    0.93
     hänen
    0.93
     his
    0.92
     kanilang
    0.87
    Activations Density 0.554%

    No Known Activations