© 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. 121911
    Prev
    Next
    INDEX
    Explanations

    patterns and tokens from structured configuration or programming code

    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
     assurent
    -0.46
    expandindo
    -0.45
    SuspendLayout
    -0.45
    PerformLayout
    -0.43
     ſtate
    -0.42
    ſelves
    -0.40
    ReusableCell
    -0.38
    EndInit
    -0.37
     karat
    -0.37
     investi
    -0.36
    POSITIVE LOGITS
    tagHelperRunner
    0.57
     protoimpl
    0.54
     Exactos
    0.50
    Derbyniad
    0.46
    ktır
    0.46
    CppMethod
    0.45
    Referanser
    0.44
     snippetHide
    0.43
     AttributeSet
    0.43
    ValueStyle
    0.42
    Activations Density 0.021%

    No Known Activations