© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 8593
    Prev
    Next
    INDEX
    Explanations

    references to methodology and processes in scientific experimentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteBarrier
    -0.74
     sendMessage
    -0.58
    fwrite
    -0.57
     Encode
    -0.55
     PUBLISH
    -0.55
     Emit
    -0.54
    AntiForgeryToken
    -0.54
    новниш
    -0.52
    ifrance
    -0.52
    Voting
    -0.52
    POSITIVE LOGITS
     collect
    1.54
     grab
    1.50
     collecting
    1.48
     collected
    1.43
     picking
    1.43
     pick
    1.42
     grabbing
    1.41
     collects
    1.40
     snatch
    1.40
    collect
    1.40
    Activations Density 0.633%

    No Known Activations