© 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
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 2596
    Prev
    Next
    INDEX
    Explanations

    terms related to infections and inflammatory processes

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

    technical or medical terminology related to medical conditions, devices, or research protocols.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    words that begin with "Inf" (such as "Infants," "Infusion," "Inflammatory," "Infectivity," "Inflator," "Inflationism," "Infirm," "Infliximab").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    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
    -0.45
    stdafx
    -0.37
    TypedDataSet
    -0.36
     lá
    -0.36
     FormGroup
    -0.36
     bré
    -0.36
    CHAPTER
    -0.35
    localctx
    -0.35
    得不
    -0.35
    ás
    -0.34
    POSITIVE LOGITS
     Inf
    0.81
     inf
    0.77
    Inf
    0.75
     INF
    0.74
    INF
    0.73
    inf
    0.67
     Infl
    0.54
     Inſ
    0.54
     infer
    0.53
     uſed
    0.51
    Activations Density 0.122%

    No Known Activations