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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-GEMMASCOPE-RES-16K
    6. 8803
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structured document markup

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ahu
    -0.53
    Geographie
    -0.50
     smir
    -0.47
     nowrap
    -0.46
     Regan
    -0.45
     Pinch
    -0.45
     APPLIC
    -0.44
    WebMethod
    -0.44
    管
    -0.44
     signific
    -0.44
    POSITIVE LOGITS
    FunctionFlags
    0.92
    enderror
    0.92
    endpush
    0.87
    endforeach
    0.85
    setVerticalGroup
    0.79
    endphp
    0.76
     {}));
    0.73
    DockStyle
    0.72
    endif
    0.68
     تضيفلها
    0.68
    Activations Density 0.178%

    No Known Activations