© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 39154
    Prev
    Next
    INDEX
    Explanations

    terms related to environments and atmospheres that promote well-being and positive interactions

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

    environment and its qualities

    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
    wäsche
    -0.42
     glan
    -0.39
    quedas
    -0.39
     التس
    -0.38
    厲害
    -0.38
    getJSONArray
    -0.37
    ocardi
    -0.37
     trouw
    -0.37
     uitgevoerd
    -0.37
    chufe
    -0.37
    POSITIVE LOGITS
     environment
    0.88
     atmosphere
    0.71
     ortam
    0.70
     Atmosphäre
    0.68
     conducive
    0.67
    environment
    0.66
     ambiente
    0.64
     surroundings
    0.63
     environments
    0.63
     ENVIRONMENT
    0.63
    Activations Density 0.028%

    No Known Activations