© 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. 9-GEMMASCOPE-RES-131K
    11. 17621
    Prev
    Next
    INDEX
    Explanations

    technical terms and classifications related to software vulnerabilities and coding practices

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

    code and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Identyfik
    -0.41
     تعدى
    -0.36
    ByExample
    -0.34
    حياته
    -0.34
    antd
    -0.34
    sequelize
    -0.33
     band
    -0.33
     modelled
    -0.33
    әһ
    -0.33
     regulador
    -0.32
    POSITIVE LOGITS
    fjspx
    0.89
    setVerticalGroup
    0.79
     utafitiHapana
    0.71
     OMITBAD
    0.70
     protoimpl
    0.66
    ništvo
    0.64
     aapt
    0.63
     переписи
    0.63
     BytesLike
    0.62
    حوالہ
    0.60
    Activations Density 0.018%

    No Known Activations