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. 20-GEMMASCOPE-RES-131K
    6. 22391
    Prev
    Next
    INDEX
    Explanations

    method calls related to retrieving or setting values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     tartalomajánló
    -0.82
    <unused79>
    -0.76
    <unused14>
    -0.75
    <unused42>
    -0.75
    [@BOS@]
    -0.75
    <unused16>
    -0.75
    <unused68>
    -0.75
    <unused28>
    -0.75
     ModelExpression
    -0.75
    <unused3>
    -0.75
    POSITIVE LOGITS
    S
    0.36
     egentligen
    0.34
    ,
    0.33
     Al
    0.33
    A
    0.32
     (
    0.31
    B
    0.31
     "
    0.30
     S
    0.30
     Schwarz
    0.30
    Activations Density 0.006%

    No Known Activations