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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 92
    Prev
    Next
    INDEX
    Explanations

    expressions and sentiments related to happiness and positivity

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

    words and phrases related to positive emotions and happiness.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     finesse
    -0.47
    JspWriter
    -0.43
    ActivityCompat
    -0.41
     Bleeding
    -0.41
     FIN
    -0.40
    kespea
    -0.40
    Gön
    -0.40
    Deborah
    -0.40
     save
    -0.40
     mergul
    -0.40
    POSITIVE LOGITS
     cheerful
    0.75
     positivity
    0.73
     smile
    0.72
     upbeat
    0.72
    happiness
    0.71
     happiness
    0.69
     smiles
    0.68
     optimism
    0.66
     smiling
    0.66
    Smile
    0.64
    Activations Density 0.176%

    No Known Activations