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. 14489
    Prev
    Next
    INDEX
    Explanations

    terms related to plumbing and home maintenance services

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

    home services and repair

    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
     صوتيه
    -0.53
    RenderAtEndOf
    -0.47
     mosso
    -0.46
     يتيمه
    -0.44
     فريبيس
    -0.43
    /**
    -0.43
    InstrumentedTest
    -0.43
    ScopeManager
    -0.42
    guiente
    -0.40
    CppCodeGen
    -0.40
    POSITIVE LOGITS
     Duel
    0.47
     homeowners
    0.43
     Bathroom
    0.43
    frontmatter
    0.40
     fireplace
    0.40
    Perfect
    0.40
    Ӕ
    0.39
     chauffage
    0.39
     Fireplace
    0.39
     hydraulic
    0.39
    Activations Density 0.009%

    No Known Activations