© 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. 28644
    Prev
    Next
    INDEX
    Explanations

    questions or phrases related to functionality and usage

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

    questions starting with "is" or "do"

    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
    TagMode
    -0.72
    PostInfinity
    -0.58
    MigrationBuilder
    -0.56
     незавершена
    -0.54
    
    -0.53
     CURIAM
    -0.51
    styleType
    -0.50
    GenerationType
    -0.49
    Clik
    -0.49
    出版年
    -0.47
    POSITIVE LOGITS
    ANTLR
    0.40
     Mus
    0.37
    يكب
    0.35
    фран
    0.34
     chemical
    0.34
     Polri
    0.33
    $_['
    0.33
     Chemical
    0.33
     Ste
    0.32
     tư
    0.32
    Activations Density 0.005%

    No Known Activations