© 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. 20-GEMMASCOPE-RES-16K
    11. 5234
    Prev
    Next
    INDEX
    Explanations

    terms related to ecological interactions and food sources in habitats

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

    specific details about prey, predation, and food consumption in scientific writing.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     AssemblyVersion
    -0.56
    djangoproject
    -0.47
    tagPool
    -0.45
     betweenstory
    -0.44
     NUKAT
    -0.44
    TagHelpers
    -0.44
    sizeCache
    -0.42
     AssemblyTitle
    -0.41
     Stodd
    -0.41
    ="@+
    -0.40
    POSITIVE LOGITS
     feeding
    0.57
    feeding
    0.54
     feed
    0.52
    diet
    0.47
     feeders
    0.47
     Feeds
    0.47
     wireType
    0.46
     feeds
    0.46
    GTCX
    0.46
     diet
    0.45
    Activations Density 0.225%

    No Known Activations