© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10779
    Prev
    Next
    INDEX
    Explanations

    references to chemical compounds and their environmental impacts

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

    "methane" (CH4) or related chemical formulas

    np_acts-logits-general · gemini-2.0-flash

    methane

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.82
     kasarigan
    -0.67
    تفصیلات
    -0.66
    PropertyChanging
    -0.66
    TypedDataSet
    -0.66
    ConstraintMaker
    -0.65
    ſelben
    -0.64
    UserScript
    -0.64
     NSCoder
    -0.64
    ьаж
    -0.64
    POSITIVE LOGITS
     methane
    0.48
     Methane
    0.43
    methane
    0.30
    rawQuery
    0.28
     bancada
    0.26
     дому
    0.26
    chließend
    0.25
    drawSprites
    0.24
    gelijk
    0.23
     offiziellen
    0.23
    Activations Density 0.263%

    No Known Activations