Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 1487
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notation involving exponents and fractions

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

    `^2`

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    SBATCH
    -0.56
    StoreMessageInfo
    -0.55
    "):
    
    -0.50
    曲は
    -0.49
    TintMode
    -0.46
    先は
    -0.44
    Gemeinden
    -0.44
    HttpPut
    -0.44
    家は
    -0.44
    はじめに
    -0.43
    POSITIVE LOGITS
    ताओं
    0.52
    ओं
    0.49
    ganet
    0.46
    bation
    0.46
    ्यों
    0.45
    istics
    0.45
    कों
    0.44
    pement
    0.42
    ത്തി
    0.42
     GenerationType
    0.42
    Activations Density 0.054%

    No Known Activations