© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 2997
    Prev
    Next
    INDEX
    Explanations

    references to application configurations and related code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -1.13
     فريبيس
    -1.01
    TagMode
    -0.97
    Vidite
    -0.94
    ьаж
    -0.91
    SourceChecksum
    -0.88
     ModelExpression
    -0.85
    denly
    -0.83
    MigrationBuilder
    -0.83
     للاسماء
    -0.82
    POSITIVE LOGITS
    <h6>
    0.58
    The
    0.56
     crimes
    0.51
     The
    0.49
    <sup>
    0.47
    ↵↵
    0.46
    endregion
    0.45
     alternativ
    0.44
     proven
    0.44
     actuaciones
    0.44
    Activations Density 0.215%

    No Known Activations