© 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. 18065
    Prev
    Next
    INDEX
    Explanations

    programming language package declarations

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

    package declarations

    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
     rather
    -0.29
    (___
    -0.26
     milliards
    -0.26
    へ
    -0.26
     startY
    -0.25
     ст
    -0.25
     revanche
    -0.25
     sainte
    -0.24
     acudi
    -0.24
    DBS
    -0.24
    POSITIVE LOGITS
    package
    2.45
     package
    1.85
     Package
    1.71
    Package
    1.66
     PACKAGE
    1.63
     packages
    1.59
     Packages
    1.52
    PACKAGE
    1.44
    packages
    1.32
    パッケージ
    1.31
    Activations Density 0.004%

    No Known Activations