Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 1870
    Prev
    Next
    INDEX
    Explanations

    numerical expressions and symbols reflecting mathematical concepts or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    classnames
    -0.79
    omock
    -0.63
    annica
    -0.60
    mybatisplus
    -0.60
    RRect
    -0.57
    (&:
    -0.56
    </thead>
    -0.55
    atleta
    -0.54
     يتيمه
    -0.53
    GEBURTS
    -0.52
    POSITIVE LOGITS
     ProtoMessage
    0.69
    styleType
    0.60
    ThroughAttribute
    0.57
    $")
    0.56
    )"),
    0.55
    djangoproject
    0.55
     كومونز
    0.51
    ValueStyle
    0.50
    SharedCtor
    0.49
     Damas
    0.49
    Activations Density 0.162%

    No Known Activations