© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 28682
    Prev
    Next
    INDEX
    Explanations

    topics related to wind energy and its environmental impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    -0.61
    tagHelperRunner
    -0.53
    RepeatedField
    -0.50
    SharedDtor
    -0.50
     actionMode
    -0.50
    webElementXpaths
    -0.50
    FieldOffsetTable
    -0.48
    verifyException
    -0.48
     udě
    -0.47
    Separate
    -0.46
    POSITIVE LOGITS
     windmill
    0.76
     wind
    0.68
     Wind
    0.65
     Renewable
    0.58
     renewable
    0.56
    Wind
    0.56
     WIND
    0.55
    fortawesome
    0.54
     turbines
    0.52
     turbine
    0.50
    Activations Density 0.010%

    No Known Activations