© 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. 21007
    Prev
    Next
    INDEX
    Explanations

    statistical data and percentages related to trends or changes

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

    percentages and proportions

    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
    ItemBackground
    -0.53
    __*/
    -0.49
     ſont
    -0.48
    Rez
    -0.48
    Rüyada
    -0.47
    OLEAN
    -0.45
     Erin
    -0.44
    Rés
    -0.44
    ADT
    -0.44
     jadx
    -0.43
    POSITIVE LOGITS
    DockStyle
    0.62
     dominance
    0.49
    setVerticalGroup
    0.45
     porcentaje
    0.44
     proportion
    0.44
    $\%
    0.44
    占比
    0.42
     proporción
    0.42
     yüzde
    0.41
    tagHelperRunner
    0.40
    Activations Density 0.060%

    No Known Activations