© 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. 22-GEMMASCOPE-RES-16K
    11. 7759
    Prev
    Next
    INDEX
    Explanations

    braces and brackets in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, URLs, and math symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -1.15
    ↵↵
    -1.13
    ,
    -1.11
     et
    -1.01
     in
    -0.99
     to
    -0.97
     der
    -0.92
     v
    -0.91
     so
    -0.90
     van
    -0.89
    POSITIVE LOGITS
     myſelf
    1.79
     itſelf
    1.73
     pleaſure
    1.66
     ſeveral
    1.58
     Monfieur
    1.55
     Diſ
    1.54
     Houſe
    1.53
     purpoſe
    1.53
     ་་
    1.50
     greateſt
    1.48
    Activations Density 0.043%

    No Known Activations