© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101415
    Prev
    Next
    INDEX
    Explanations

    references to data retrieval and data structures

    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
    RegressionTest
    -0.87
    tvguidetime
    -0.76
    MigrationBuilder
    -0.70
    
    -0.69
    MLLoader
    -0.69
    AndEndTag
    -0.66
     JpaRepository
    -0.59
    OGND
    -0.59
    extAlignment
    -0.59
    ThroughAttribute
    -0.57
    POSITIVE LOGITS
    rinfo
    0.45
    Jereo
    0.35
     Sie
    0.32
     Bellamy
    0.32
     Zac
    0.32
     legal
    0.31
     body
    0.31
     map
    0.31
    rive
    0.31
     du
    0.31
    Activations Density 0.174%

    No Known Activations