© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11081
    Prev
    Next
    INDEX
    Explanations

    programming-related terms, especially those involving modifications or updates

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

    "_set" or "Mutable" in code

    np_acts-logits-general · gemini-2.0-flash

    setting or modifying values

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    toMatchSnapshot
    -0.37
    jsonwebtoken
    -0.34
     Picchu
    -0.31
    越多
    -0.29
    RLock
    -0.28
    ljeno
    -0.28
    openConnection
    -0.28
    liculas
    -0.28
    Xna
    -0.27
     насла
    -0.27
    POSITIVE LOGITS
    IsMutable
    0.67
    WritableDatabase
    0.60
     CascadeType
    0.57
    RTEE
    0.57
    writeField
    0.56
     GenerationType
    0.56
    InputBorder
    0.55
    parsedMessage
    0.55
     Comprometido
    0.54
     ContentValues
    0.53
    Activations Density 0.503%

    No Known Activations