© 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. 3-GEMMASCOPE-RES-16K
    6. 13097
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics pertaining to health or well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیای
    -0.70
    RenderAtEndOf
    -0.69
    thâu
    -0.66
     թվական
    -0.62
    ).__
    -0.62
    WriteAttribute
    -0.61
    +#+
    -0.59
    UrlResolution
    -0.58
     mergeFrom
    -0.55
    </thead>
    -0.54
    POSITIVE LOGITS
     EconPapers
    0.69
     AssemblyCompany
    0.60
    లాలు
    0.60
     typelib
    0.51
     initComponents
    0.51
    Intérieur
    0.50
    AndroidJUnit
    0.48
    \
    0.48
    ThroughAttribute
    0.48
     <<<<<<<<<<<<<<
    0.48
    Activations Density 0.228%

    No Known Activations