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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113759
    Prev
    Next
    INDEX
    Explanations

    HTML table headers

    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
     ואת
    -0.38
     uses
    -0.38
    use
    -0.37
     or
    -0.36
     use
    -0.35
    userID
    -0.35
    mantec
    -0.34
    or
    -0.34
     pun
    -0.33
     fiches
    -0.32
    POSITIVE LOGITS
    </thead>
    4.41
    </tfoot>
    1.48
    MigrationBuilder
    1.05
     nakalista
    0.94
    setVerticalGroup
    0.94
    RegressionTest
    0.91
    httphttps
    0.89
    DebuggerNonUser
    0.89
    enterOuterAlt
    0.86
    expandindo
    0.86
    Activations Density 0.000%

    No Known Activations