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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 11324
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to definitions, inequalities, and conditions in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ри
    -0.50
    <strong>
    -0.50
     dem
    -0.49
    ana
    -0.49
     {
    -0.48
    ране
    -0.47
    bilecek
    -0.47
     Bis
    -0.46
     a
    -0.46
     sobre
    -0.46
    POSITIVE LOGITS
    oredCriteria
    0.98
    rrggbb
    0.87
    FieldBuilder
    0.85
     raiſ
    0.84
    存于互联网档案馆
    0.84
     myſelf
    0.83
     occaf
    0.82
     poffible
    0.81
     himſelf
    0.80
     purpoſe
    0.79
    Activations Density 0.706%

    No Known Activations