© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 55908
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to the impact and effects of various factors on different subjects

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

    effect or impact of

    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
     للمعارف
    -0.41
     löytyy
    -0.39
     HttpNotFound
    -0.39
     Gründen
    -0.39
     rejoindre
    -0.36
     löyty
    -0.35
     menant
    -0.34
    chieht
    -0.34
    ElementException
    -0.34
     sayfas
    -0.34
    POSITIVE LOGITS
     influence
    1.09
     impact
    1.05
    influence
    0.98
    impact
    0.95
     affect
    0.94
     impacts
    0.92
    Impact
    0.92
    Influence
    0.91
     Influence
    0.90
     Impact
    0.90
    Activations Density 0.253%

    No Known Activations