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. 31-GEMMASCOPE-RES-131K
    6. 38152
    Prev
    Next
    INDEX
    Explanations

    factors that indicate specific conditions or experiences related to time and weather in narrative contexts

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

    articles before days or weather

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     tartalomajánló
    -0.48
     AssemblyTitle
    -0.47
     Normdatei
    -0.46
    audiovisuel
    -0.43
     AssemblyProduct
    -0.42
     AssemblyVersion
    -0.41
    دانشنامهٔ
    -0.40
    oa̍t
    -0.40
     ब्रेकडाउन
    -0.40
    ⟬
    -0.38
    POSITIVE LOGITS
     sunny
    0.93
     rainy
    0.75
     day
    0.74
     cloudy
    0.69
     overcast
    0.69
    sunny
    0.68
     weekday
    0.67
     Saturday
    0.62
     chilly
    0.61
     Wednesday
    0.60
    Activations Density 0.052%

    No Known Activations