© 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. 12496
    Prev
    Next
    INDEX
    Explanations

    postal codes or geographic identifiers

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

    <start_of_turn>user

    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
    
    -0.60
    <unused68>
    -0.60
    <unused42>
    -0.60
    <unused79>
    -0.60
    <unused23>
    -0.60
    <unused16>
    -0.60
    <unused52>
    -0.59
     メンテナ
    -0.59
    <unused41>
    -0.59
    [@BOS@]
    -0.59
    POSITIVE LOGITS
    AppMethodBeat
    0.45
    shadowOffset
    0.43
    useNewUrlParser
    0.40
    RectangleBorder
    0.37
    WriteBarrier
    0.32
    Downtown
    0.30
     Sal
    0.29
     OnTriggerEnter
    0.29
    localStorage
    0.28
     town
    0.28
    Activations Density 0.001%

    No Known Activations