© 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. 29995
    Prev
    Next
    INDEX
    Explanations

    words related to assistance or support

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

    providing assistance or beneficial outcomes

    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
     tenisky
    -0.41
    glLoad
    -0.40
    dawnictwo
    -0.38
     McDonnell
    -0.37
     Kün
    -0.37
    kwür
    -0.37
     erfaren
    -0.36
    çoivent
    -0.35
     valuations
    -0.35
    enegro
    -0.35
    POSITIVE LOGITS
    WebVitals
    0.62
    expandindo
    0.61
    tagHelperRunner
    0.57
    AndEndTag
    0.57
    MessageTagHelper
    0.52
    ContentAsync
    0.52
    extAlignment
    0.51
    principalColumn
    0.50
    ValueStyle
    0.50
     Comprometido
    0.48
    Activations Density 0.004%

    No Known Activations