© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3633
    Prev
    Next
    INDEX
    Explanations

    specific codes or identifiers typically found in technical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Hexadecimal values

    np_acts-logits-general · gemini-2.0-flash

    sequences like `0xb`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ligiloj
    -0.51
    richting
    -0.50
    perspective
    -0.48
     currentState
    -0.47
    point
    -0.47
     Conditioner
    -0.46
     Daley
    -0.45
    state
    -0.45
     conditioners
    -0.45
    estroyer
    -0.45
    POSITIVE LOGITS
    b
    0.75
     b
    0.67
    B
    0.66
    bbbb
    0.65
    sb
    0.64
    db
    0.64
    ub
    0.63
     getB
    0.63
    bb
    0.62
     HB
    0.62
    Activations Density 0.958%

    No Known Activations