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. 45545
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to drug use and its paraphernalia

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

    drug paraphernalia and substances

    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
    ChildIndex
    -0.23
     cấp
    -0.23
    entityManager
    -0.23
    InitVars
    -0.23
    ordnen
    -0.22
     internes
    -0.22
    entreprise
    -0.22
     kazi
    -0.22
     politiques
    -0.22
     important
    -0.22
    POSITIVE LOGITS
     nakalista
    0.81
    OGND
    0.78
    astify
    0.77
     ModelExpression
    0.75
     betweenstory
    0.75
     disambiguazione
    0.73
    RTDA
    0.73
    AsUp
    0.73
    aarrggbb
    0.72
     resourceCulture
    0.71
    Activations Density 0.004%

    No Known Activations