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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15451
    Prev
    Next
    INDEX
    Explanations

    dialogue and interactions between characters

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

    Follows a speech verb

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.60
     betweenstory
    -0.59
    تقاوى
    -0.54
    transQ
    -0.52
     noDo
    -0.52
    httphttps
    -0.50
    UrlResolution
    -0.49
     urme
    -0.49
    abestanden
    -0.47
     nonUne
    -0.47
    POSITIVE LOGITS
     nonchal
    0.69
     calmly
    0.69
     excitedly
    0.66
     smiling
    0.65
     cheerfully
    0.62
     confidently
    0.60
     sambil
    0.60
     casually
    0.60
     softly
    0.59
     sweetly
    0.59
    Activations Density 0.135%

    No Known Activations