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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 3352
    Prev
    Next
    INDEX
    Explanations

    elements related to personal success and business relationships

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

    following possessive adjectives

    np_acts-logits-general · gemini-2.0-flash

    ownbusiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.73
    seamnă
    -0.70
    windowFixed
    -0.66
    IVEREF
    -0.65
     disambiguazione
    -0.64
     quelcon
    -0.59
     récentes
    -0.56
     esternos
    -0.56
     étudi
    -0.56
     crainte
    -0.56
    POSITIVE LOGITS
     mini
    0.64
     referenties
    0.56
    styleType
    0.56
    UnsafeEnabled
    0.54
    miniature
    0.53
     Wikimedijinoj
    0.52
    醐
    0.52
     miniature
    0.51
     virtual
    0.51
    셈
    0.50
    Activations Density 0.336%

    No Known Activations