© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 90235
    Prev
    Next
    INDEX
    Explanations

    instructions related to adding ingredients and mixing in cooking or chemical processes

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

    adding or injecting materials slowly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatelessWidget
    -0.61
    waffle
    -0.56
    点此举报
    -0.56
    __":
    
    -0.56
    __':
    
    -0.55
     Chwiliwch
    -0.54
    BASEPATH
    -0.53
     StatefulWidget
    -0.50
    ripe
    -0.49
    racite
    -0.49
    POSITIVE LOGITS
    ContentAsync
    0.39
    BufferException
    0.35
    velocityY
    0.34
     manualmente
    0.33
     ilma
    0.30
     ffilmiau
    0.29
     Slowly
    0.29
    sizePolicy
    0.29
    CascadeType
    0.28
    JoinTable
    0.28
    Activations Density 0.009%

    No Known Activations