© 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 EvalsExportsinterp-engineNEWAPI 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. 16781
    Prev
    Next
    INDEX
    Explanations

    instances of exposure to various topics or elements

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

    exposure to

    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
    Not in Any Lists

    No Comments

    Negative Logits
     provisoire
    -0.52
     argint
    -0.51
    ambiguation
    -0.44
    atience
    -0.43
     ProgressDialog
    -0.42
    хьтан
    -0.41
     sendo
    -0.41
     tendance
    -0.40
    ginate
    -0.40
     nueces
    -0.40
    POSITIVE LOGITS
     exposure
    0.82
    Exposure
    0.77
    Expose
    0.70
     exposures
    0.68
     Exposure
    0.67
     EXPOSURE
    0.65
    exposure
    0.64
     exposed
    0.63
    Exposed
    0.62
    Encounter
    0.61
    Activations Density 0.024%

    No Known Activations