© 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
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5491
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or points of interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulose
    -0.52
     tervez
    -0.51
    formik
    -0.51
     plufieurs
    -0.48
     kiệm
    -0.48
    WebElementEntity
    -0.47
    returnType
    -0.47
     Validation
    -0.46
    Życiorys
    -0.45
    原始内容存档于
    -0.45
    POSITIVE LOGITS
     spot
    1.59
    spot
    1.49
     spots
    1.41
     Spot
    1.40
    Spot
    1.39
     SPOT
    1.35
    spots
    1.30
     Spots
    1.22
    SPOT
    1.20
    Spots
    1.15
    Activations Density 0.182%

    No Known Activations