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. 68530
    Prev
    Next
    INDEX
    Explanations

    expressions and words that convey positivity and uplifting sentiments

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

    cheerful and happy feelings

    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
    adaptiveStyles
    -0.46
    帖最后由
    -0.44
    writeFieldEnd
    -0.40
     SUDOC
    -0.37
    PostInfinity
    -0.36
    rewsbury
    -0.36
     GetEnumerator
    -0.35
    🔕
    -0.35
    ginas
    -0.35
     Winaray
    -0.34
    POSITIVE LOGITS
     cheerful
    0.68
     joyous
    0.67
     alegre
    0.66
    cheerful
    0.64
     alegría
    0.64
     cheerfully
    0.63
     joyful
    0.62
     upbeat
    0.61
     joyeux
    0.58
     joyfully
    0.57
    Activations Density 0.011%

    No Known Activations