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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14480
    Prev
    Next
    INDEX
    Explanations

    references to health risks associated with mold and other environmental toxins

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

    health risks and exposure

    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
    lencia
    -0.34
    wörter
    -0.31
     گ
    -0.31
     Silber
    -0.31
    SB
    -0.28
     clunky
    -0.28
    currentColor
    -0.28
     embarrassing
    -0.28
     pom
    -0.27
     vel
    -0.27
    POSITIVE LOGITS
    ValueStyle
    0.76
    tagHelperRunner
    0.71
    pecabe
    0.62
    BufferException
    0.59
    AllowUser
    0.56
    PyExc
    0.56
     illnesses
    0.56
    ésultats
    0.55
    DJANGO
    0.54
    AddTagHelper
    0.54
    Activations Density 0.024%

    No Known Activations