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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 12628
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to layers and thickness in materials science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.79
     GetEnumerator
    -0.73
    ⓧ
    -0.63
     ISNI
    -0.57
    новниш
    -0.56
    ThroughAttribute
    -0.56
    ipzig
    -0.56
    iredo
    -0.56
     Италијани
    -0.56
     ivelany
    -0.56
    POSITIVE LOGITS
     layers
    1.23
     layer
    1.10
     Layers
    1.07
    layers
    1.06
    Layers
    1.03
     LAYER
    0.95
    layer
    0.93
     layering
    0.90
     Schichten
    0.89
    LAYER
    0.88
    Activations Density 0.489%

    No Known Activations