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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1121
    Prev
    Next
    INDEX
    Explanations

    programming and coding constructs related to AWS services and resource management

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

    AWS Kinesis Data Firehose commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.70
    UnusedPrivate
    -0.69
     Wikispecies
    -0.69
    contentLoaded
    -0.66
    EndInit
    -0.64
    tonode
    -0.62
    ValueStyle
    -0.61
    LLocation
    -0.61
    awtextra
    -0.60
    setof
    -0.59
    POSITIVE LOGITS
    служба
    0.34
     tebal
    0.32
     Crisp
    0.31
     azt
    0.30
    abo
    0.30
    britannien
    0.30
    getFirstName
    0.29
    SetOutput
    0.28
     scattata
    0.28
    à
    0.28
    Activations Density 0.017%

    No Known Activations