© 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. 112173
    Prev
    Next
    INDEX
    Explanations

    sections of code or documentation that reference omitted sections or features

    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
    IBOutlet
    -0.46
     propOrder
    -0.46
     cubierto
    -0.39
    ="@+
    -0.38
     démocratique
    -0.38
     &___
    -0.38
     baby
    -0.38
    transQ
    -0.37
     panggilan
    -0.37
    DBNull
    -0.36
    POSITIVE LOGITS
    fml
    4.31
    FML
    1.52
    gdx
    0.59
    +#+
    0.59
    minecraftforge
    0.57
    HasAnnotation
    0.57
    الحياه
    0.56
    CodeAttribute
    0.55
    UserScript
    0.53
     Fm
    0.52
    Activations Density 0.000%

    No Known Activations