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. 11684
    Prev
    Next
    INDEX
    Explanations

    references to numerical values, specifically focusing on various data inputs

    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
     autorytatywna
    -0.85
     Bho
    -0.80
     Janis
    -0.78
    ,:);
    -0.74
    fastjson
    -0.71
     Hairst
    -0.71
     fes
    -0.70
    )*/
    -0.70
     Hecho
    -0.69
    MessageInfo
    -0.69
    POSITIVE LOGITS
    dersfield
    0.71
    mill
    0.68
    0
    0.67
    dymyr
    0.67
    postsleuth
    0.62
     المتحدة
    0.61
     fuerzas
    0.60
    uu
    0.60
    eseed
    0.60
     Hundred
    0.60
    Activations Density 0.398%

    No Known Activations