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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 22373
    Prev
    Next
    INDEX
    Explanations

    concepts related to self-awareness and personal development

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

    Abstract nouns and phrases related to spirituality, consciousness, personal growth, and inner experience, often appearing in self-help, philosophical, or spiritual contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     للاسماء
    -0.64
     NSCoder
    -0.63
    HtmlAttribute
    -0.56
    ViewFeatures
    -0.56
     gynhyrchwyd
    -0.54
    calvin
    -0.51
     Angry
    -0.50
    httphttps
    -0.50
    bootstrapcdn
    -0.50
    rably
    -0.49
    POSITIVE LOGITS
     yoga
    0.50
     yog
    0.49
     chakras
    0.45
     healing
    0.44
    ulemon
    0.42
     healers
    0.41
    Yoga
    0.41
    healing
    0.40
     healer
    0.40
     Yoga
    0.39
    Activations Density 0.117%

    No Known Activations