© 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. 44635
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes and procedures, particularly in technical contexts

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

    words following specific tokens

    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
    casted
    -0.82
    webElementXpaths
    -0.73
     advancements
    -0.71
     niks
    -0.69
     Zeitraum
    -0.68
     Anyways
    -0.68
    Anyways
    -0.66
     blurry
    -0.66
     detrimental
    -0.66
     aforementioned
    -0.65
    POSITIVE LOGITS
     muß
    0.60
    faßt
    0.59
     daß
    0.57
    reszcie
    0.54
     läßt
    0.49
    ❦
    0.46
     daarvan
    0.46
     weitgehend
    0.45
     variously
    0.45
     occorre
    0.44
    Activations Density 2.635%

    No Known Activations