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. 3579
    Prev
    Next
    INDEX
    Explanations

    user interface elements and interactions in a digital context

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

    icon, arrow, dot, more

    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
    awtextra
    -0.49
     aufzu
    -0.39
    didSet
    -0.39
    ContentAsync
    -0.36
    TYPED
    -0.35
     parseFrom
    -0.34
    ActiveRecord
    -0.33
    /**
    -0.33
    rungsseite
    -0.33
    enumi
    -0.32
    POSITIVE LOGITS
    contentLoaded
    0.59
    createStatement
    0.52
     AttributeSet
    0.48
     BEHIND
    0.48
    ArrowToggle
    0.48
    Panamoan
    0.47
     Persson
    0.46
    ⤹
    0.46
     COMPLEX
    0.46
     WebDriverWait
    0.46
    Activations Density 0.008%

    No Known Activations