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. 120860
    Prev
    Next
    INDEX
    Explanations

    references to programming elements or components in structured code

    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
    WritableDatabase
    -0.26
    Попис
    -0.24
     nahilalakip
    -0.24
    ),),
    -0.23
     keyPressed
    -0.22
    }))
    -0.21
    もありますが
    -0.21
    InstrumentedTest
    -0.21
    OCCURRED
    -0.20
    autoreleasepool
    -0.20
    POSITIVE LOGITS
    <unused14>
    0.99
    <unused28>
    0.99
    [@BOS@]
    0.99
    <unused17>
    0.98
    <unused51>
    0.98
    <pad>
    0.98
    <unused23>
    0.98
    <unused42>
    0.98
    <unused41>
    0.98
    <unused3>
    0.98
    Activations Density 0.033%

    No Known Activations