Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 51895
    Prev
    Next
    INDEX
    Explanations

    technical terms and measurements related to scientific and mathematical concepts

    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
    IUrlHelper
    -0.75
     ThemeData
    -0.66
    MLLoader
    -0.64
    Datuak
    -0.63
     Roskov
    -0.63
    adpleegd
    -0.60
    ']>;
    -0.60
    parsedMessage
    -0.59
     يتيمه
    -0.59
    الحياه
    -0.59
    POSITIVE LOGITS
    avaj
    0.40
    IALLY
    0.40
    IMES
    0.39
    VERT
    0.39
    listo
    0.39
    趣
    0.38
    TOR
    0.38
    OW
    0.37
    Bed
    0.36
    KER
    0.36
    Activations Density 0.121%

    No Known Activations