© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1433
    Prev
    Next
    INDEX
    Explanations

    terms and expressions related to templates and structured formats

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

    starting with "temp" or "amp"

    np_acts-logits-general · gemini-2.0-flash

    temperature, template, camp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    躇
    -0.46
    sous
    -0.44
    rights
    -0.43
    GetAxis
    -0.43
     Jurí
    -0.42
     soin
    -0.41
     getKey
    -0.41
     jurí
    -0.41
     Rite
    -0.41
     rowIndex
    -0.41
    POSITIVE LOGITS
     Camp
    0.82
    Camp
    0.80
     Camper
    0.78
     camp
    0.74
    camp
    0.74
     Camps
    0.73
    mpu
    0.73
    CAMP
    0.71
     Pamp
    0.71
     AMP
    0.70
    Activations Density 0.299%

    No Known Activations