© 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. 101178
    Prev
    Next
    INDEX
    Explanations

    references to interactions or relationships involving people, particularly in a legal or customer context

    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
     виправивши
    -0.56
    DockStyle
    -0.55
    twimg
    -0.52
    enumii
    -0.51
     estekak
    -0.50
    stdc
    -0.49
    Péri
    -0.48
    #+#
    -0.47
    ----</
    -0.45
     defaultstate
    -0.45
    POSITIVE LOGITS
    SourceChecksum
    0.42
     heard
    0.39
    protoimpl
    0.39
    getMenuInflater
    0.38
     gjerne
    0.38
    SupportActionBar
    0.38
     disponibilités
    0.37
    extAlignment
    0.36
     guessed
    0.35
    appé
    0.34
    Activations Density 0.106%

    No Known Activations