© 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. 101838
    Prev
    Next
    INDEX
    Explanations

    instances of "withholding" and its variations, particularly in legal contexts

    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
    Slf
    -0.68
     Signalez
    -0.51
    //
    -0.50
    enumi
    -0.49
    ApiOperation
    -0.48
    SuspendLayout
    -0.48
    ActionCreators
    -0.47
    Dre
    -0.47
    JMenu
    -0.46
    Lay
    -0.45
    POSITIVE LOGITS
    <bos>
    0.53
     Wavelength
    0.50
     mediano
    0.47
    RestTemplate
    0.47
     websocket
    0.47
    Subnet
    0.46
     primas
    0.46
     desmotivaciones
    0.46
    istocene
    0.46
     barbati
    0.46
    Activations Density 0.020%

    No Known Activations