© 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. 9-GEMMASCOPE-RES-16K
    11. 1603
    Prev
    Next
    INDEX
    Explanations

    references to scientific potential and analysis within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.03
     ainfi
    -0.96
     ſtate
    -0.92
     Houſe
    -0.89
     themſelves
    -0.88
     $_(
    -0.88
     Theſe
    -0.86
    ſelf
    -0.85
     Reſ
    -0.85
     合集
    -0.85
    POSITIVE LOGITS
     
    0.72
     or
    0.64
     and
    0.58
     very
    0.53
     in
    0.50
    ,
    0.49
     has
    0.49
     H
    0.49
     a
    0.48
     A
    0.48
    Activations Density 0.863%

    No Known Activations