© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 105543
    Prev
    Next
    INDEX
    Explanations

    references to investigations and arrests in legal contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     ovunque
    -0.45
    XtraEditors
    -0.44
     للاسماء
    -0.44
    RenderAtEndOf
    -0.44
    ecake
    -0.43
    udara
    -0.43
     UserController
    -0.42
     CreateTagHelper
    -0.42
    Anth
    -0.42
     aturan
    -0.41
    POSITIVE LOGITS
    脚注の使い方
    0.46
     investigators
    0.42
    mybatisplus
    0.42
     investigation
    0.41
     insuffisamment
    0.40
     investigations
    0.38
    quias
    0.38
    gráficos
    0.36
     investigating
    0.35
    investig
    0.35
    Activations Density 0.050%

    No Known Activations