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. 113969
    Prev
    Next
    INDEX
    Explanations

    imperative and suggestion phrases aimed at guiding actions

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

    can followed by verb

    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
    ロウィン
    -0.77
    tagHelperRunner
    -0.76
     NSCoder
    -0.75
    ſelben
    -0.75
    tvguidetime
    -0.73
     wiſſen
    -0.73
     ſehen
    -0.70
    AddTagHelper
    -0.68
    ſicht
    -0.68
     ſeyn
    -0.68
    POSITIVE LOGITS
     ceinture
    0.37
     TAMBIÉN
    0.28
    Werke
    0.27
     Thank
    0.27
    DoubleQuotes
    0.27
     cuisson
    0.26
     uñas
    0.26
    False
    0.26
     fallas
    0.26
     False
    0.25
    Activations Density 0.001%

    No Known Activations