© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 96655
    Prev
    Next
    INDEX
    Explanations

    coding functions and methods related to data handling and API interactions

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

    places and contexts

    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
     eût
    -0.44
    jahtera
    -0.39
     {:
    -0.34
     Aff
    -0.32
     sail
    -0.31
     regeringen
    -0.30
    ofday
    -0.30
    URRED
    -0.30
    swire
    -0.29
     szár
    -0.29
    POSITIVE LOGITS
     EconPapers
    1.52
    HttpPut
    1.43
    HttpGet
    1.42
    HttpPost
    1.27
    AddRange
    1.17
    HttpDelete
    1.09
    Ссылки
    1.01
    onViewCreated
    0.82
    SequentialGroup
    0.81
     ***!
    0.79
    Activations Density 0.001%

    No Known Activations