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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 108320
    Prev
    Next
    INDEX
    Explanations

    terms related to weather conditions and forecasts

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

    sea and weather conditions

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Personendaten
    -0.60
    ConstraintMaker
    -0.58
     AssemblyCompany
    -0.56
    GraphicsUnit
    -0.55
    majánló
    -0.50
     kaynağından
    -0.50
     utafitiHapana
    -0.50
     оригіналу
    -0.49
     arşivlendi
    -0.46
     estekak
    -0.45
    POSITIVE LOGITS
    weather
    0.41
     suspended
    0.38
     weather
    0.37
     Medium
    0.37
     urged
    0.36
     medium
    0.36
     Meteorological
    0.35
    therm
    0.35
    Weather
    0.35
    <caption>
    0.35
    Activations Density 0.005%

    No Known Activations