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. 24-GEMMASCOPE-RES-16K
    6. 953
    Prev
    Next
    INDEX
    Explanations

    legal references and citations in legal texts

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

    Text within parentheses, especially citations or quotations

    np_acts-logits-general · gemini-2.0-flash

    parenthetical citations and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spar
    -0.28
     spal
    -0.28
    ofer
    -0.28
    ficar
    -0.28
     рассказа
    -0.28
    talk
    -0.27
     Bure
    -0.27
     кул
    -0.27
     stories
    -0.27
    brough
    -0.27
    POSITIVE LOGITS
    EDEFAULT
    0.78
     quoted
    0.75
     quote
    0.75
    ValueStyle
    0.75
    emphasis
    0.74
     nakalista
    0.71
    Emphasis
    0.71
     quoting
    0.67
    Hentet
    0.66
     Quoted
    0.65
    Activations Density 0.507%

    No Known Activations