© 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. 111740
    Prev
    Next
    INDEX
    Explanations

    phrases related to policies, permissions, and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    parsedMessage
    -0.77
     kasarigan
    -0.75
    GraphicsUnit
    -0.71
     surla
    -0.69
    ViewInit
    -0.66
    BeginContext
    -0.65
    MLLoader
    -0.64
    GTCX
    -0.64
     CanadaChoose
    -0.63
     snippetHide
    -0.61
    POSITIVE LOGITS
     yourself
    0.37
     Libertadores
    0.37
     yourselves
    0.35
     war
    0.35
     before
    0.34
     xem
    0.33
     look
    0.32
     tikra
    0.32
     kiek
    0.32
     YOURSELF
    0.32
    Activations Density 0.035%

    No Known Activations