© 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 EvalsExportsAPI 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. 15521
    Prev
    Next
    INDEX
    Explanations

    technical or scientific notation and terms associated with data analysis and processing

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

    Mathematical or numerical expressions

    np_acts-logits-general · gemini-2.0-flash

    ΔCt and peak baseline

    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
    󠁣
    -0.77
    posedge
    -0.75
     мәкал
    -0.74
     zijne
    -0.73
    MigrationBuilder
    -0.71
    Personendaten
    -0.68
     CreateTagHelper
    -0.68
     NSCoder
    -0.67
    devamını
    -0.66
     propOrder
    -0.65
    POSITIVE LOGITS
     HH
    0.53
     Popov
    0.51
    ww
    0.49
     ww
    0.49
     bab
    0.49
    WW
    0.48
     bb
    0.48
    MM
    0.47
    bb
    0.46
    subsubsection
    0.45
    Activations Density 1.663%

    No Known Activations