© 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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104764
    Prev
    Next
    INDEX
    Explanations

    legal references or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    AddTagHelper
    -0.91
    OGND
    -0.91
    MigrationBuilder
    -0.84
     Chwiliwch
    -0.75
    saraba
    -0.72
    AndEndTag
    -0.71
    Autoritní
    -0.69
    sizeCache
    -0.69
    httphttps
    -0.68
     فريبيس
    -0.68
    POSITIVE LOGITS
     enfans
    0.37
     createSlice
    0.37
    viembre
    0.37
     reglas
    0.36
     abond
    0.35
     Freiheit
    0.34
     rescate
    0.34
     nám
    0.33
     conseils
    0.33
     conservación
    0.33
    Activations Density 0.104%

    No Known Activations