© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5195
    Prev
    Next
    INDEX
    Explanations

    statements of actions and interactions relating to authority and consequences

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

    Precedes a pronoun referring to a female

    np_acts-logits-general · gemini-2.0-flash

    she or her

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     her
    -1.11
     suaminya
    -1.10
     herself
    -0.99
    herself
    -0.97
    her
    -0.90
    Her
    -0.85
     ihn
    -0.76
     honom
    -0.76
     Her
    -0.74
     hennes
    -0.73
    POSITIVE LOGITS
     she
    1.53
    She
    1.05
     She
    0.94
     она
    0.89
     wives
    0.86
     wife
    0.85
    she
    0.79
     WIFE
    0.78
     ela
    0.78
    ViewFeatures
    0.78
    Activations Density 0.278%

    No Known Activations