© 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. 122653
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to public methods and dialog handling

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

    code parsing and generation

    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
    ########.
    -0.68
     '\\;'
    -0.63
    Véxase
    -0.58
    Personendaten
    -0.52
    Donnell
    -0.50
     متعلقه
    -0.50
     kebaya
    -0.49
    bleau
    -0.49
    AndEndTag
    -0.48
     Bioaccumulative
    -0.48
    POSITIVE LOGITS
    OpenHelper
    0.87
    principalTable
    0.45
    MemoryWarning
    0.39
    enterOuterAlt
    0.35
     nas
    0.34
    UseVisualStyle
    0.32
    InitVars
    0.32
     Spr
    0.29
    queryInterface
    0.28
     Tind
    0.28
    Activations Density 0.000%

    No Known Activations