© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 40575
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing commitment or dedication

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

    to + action

    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
     popcorn
    -0.48
    HttpContext
    -0.42
    popcorn
    -0.41
     Hoang
    -0.41
    AutoScaleMode
    -0.41
    OCCURRED
    -0.40
    ahalli
    -0.40
     curio
    -0.40
     reporter
    -0.40
     lexer
    -0.40
    POSITIVE LOGITS
     udrž
    0.59
     maintaining
    0.58
     murni
    0.58
     rangka
    0.57
    致力于
    0.55
     achieving
    0.55
     ensuring
    0.54
     realizacji
    0.54
    tahankan
    0.54
     utrzy
    0.54
    Activations Density 0.008%

    No Known Activations