Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 52479
    Prev
    Next
    INDEX
    Explanations

    technical terms, scientific measurements, and references to equipment or methodologies in research

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

    court cases and legal citations

    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
    Personendaten
    -0.75
     bezeichneter
    -0.74
     Мексичка
    -0.69
    GOTREF
    -0.67
     Wikiseite
    -0.60
     Roskov
    -0.60
    Manbalar
    -0.59
    Geografía
    -0.57
    antaranya
    -0.57
    SharedCtor
    -0.56
    POSITIVE LOGITS
    #
    0.63
    0.48
    gua
    0.47
    dia
    0.47
    iol
    0.46
    mias
    0.46
    wadi
    0.46
    Dem
    0.46
    duc
    0.45
    iform
    0.45
    Activations Density 1.777%

    No Known Activations