© 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. 123172
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms related to materials, electrical properties, and legal or financial context

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

    hip-hop pioneer, inhibitory compounds, polyimide synthetic

    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
    httphttps
    -0.86
    OGND
    -0.86
    省市镇
    -0.78
    RegressionTest
    -0.76
    ніципалі
    -0.69
    LLocation
    -0.68
     autorytatywna
    -0.66
    帖最后由
    -0.64
     للمعارف
    -0.63
    ExtendWith
    -0.62
    POSITIVE LOGITS
     muñ
    0.30
     gobern
    0.29
    Wnd
    0.29
     bezeichneter
    0.28
     avto
    0.28
     probado
    0.27
     hubiese
    0.26
     Jesucristo
    0.26
     contraire
    0.25
     professeur
    0.25
    Activations Density 0.023%

    No Known Activations