© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 31192
    Prev
    Next
    INDEX
    Explanations

    keywords and terms relevant to data analysis and scientific research

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

    affairs, Astrophysics, Econometrica, toppers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المكان
    -0.32
    ReadInt
    -0.31
     cargo
    -0.29
     Heavy
    -0.29
     Slov
    -0.28
    Military
    -0.28
    Heavy
    -0.28
    整
    -0.27
     δικ
    -0.27
     pavo
    -0.27
    POSITIVE LOGITS
    toppers
    2.89
     Stoppers
    2.47
    topper
    1.59
     toppers
    1.30
     topper
    1.22
    stopper
    1.14
     stopper
    1.05
    topping
    0.77
    NameInMap
    0.71
    ftagPool
    0.71
    Activations Density 0.002%

    No Known Activations