© 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. 21-GEMMASCOPE-RES-16K
    11. 13875
    Prev
    Next
    INDEX
    Explanations

    references to health benefits and bioactive compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     szól
    -0.41
     BoxDecoration
    -0.41
    belajaran
    -0.39
     malheur
    -0.38
    行政区划
    -0.38
     dangerous
    -0.38
    [];
    -0.38
     Geste
    -0.37
     steers
    -0.37
    _;
    -0.37
    POSITIVE LOGITS
    AndEndTag
    0.44
    SharedCtor
    0.43
    TagMode
    0.40
    蚪
    0.40
    AllowUser
    0.39
    improve
    0.38
    printLine
    0.38
     Improve
    0.38
    BeginContext
    0.38
    Improve
    0.38
    Activations Density 0.180%

    No Known Activations