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. 7-GEMMASCOPE-RES-16K
    6. 15009
    Prev
    Next
    INDEX
    Explanations

    closing brackets and parentheses in code

    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
     Lili
    -0.96
     Elli
    -0.94
    “……
    -0.92
    úde
    -0.88
     Kes
    -0.87
    voorbeeld
    -0.86
    >>>>
    -0.85
     Hirst
    -0.84
    pects
    -0.83
    Lili
    -0.83
    POSITIVE LOGITS
     Pisa
    0.83
    {{
    0.82
     Wendell
    0.79
     Mónica
    0.76
    emerald
    0.75
    ,,,
    0.75
     Pequ
    0.75
     WebApplication
    0.75
    CAPTCHA
    0.73
    choline
    0.73
    Activations Density 0.264%

    No Known Activations