© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 8522
    Prev
    Next
    INDEX
    Explanations

    versioning and compatibility information related to software or hardware systems

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    software versioning and API levels

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    Needs
    -0.39
    iac
    -0.38
     appetites
    -0.38
    ᅠ
    -0.36
    Datuak
    -0.36
    ✏️
    -0.36
    áctenos
    -0.35
    sights
    -0.35
    FAN
    -0.35
    Архівовано
    -0.35
    POSITIVE LOGITS
     AssemblyCulture
    0.67
    VERSION
    0.59
     AssemblyVersion
    0.56
    ValueStyle
    0.51
    CodeAttribute
    0.49
    ConstraintMaker
    0.48
     TestBed
    0.48
    userAgent
    0.47
     invokingState
    0.46
    ActivityCompat
    0.45
    Activations Density 0.003%

    No Known Activations