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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 8080
    Prev
    Next
    INDEX
    Explanations

    references to mathematical roots and root systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Viitteet
    -0.70
    dafx
    -0.61
     Réponses
    -0.59
    ########.
    -0.58
    WebElementEntity
    -0.53
    Friends
    -0.53
     Friends
    -0.52
     Auff
    -0.51
    cshtml
    -0.51
    ongyang
    -0.49
    POSITIVE LOGITS
    Cause
    0.72
     cause
    0.70
     Cause
    0.67
    cause
    0.67
    stocks
    0.63
    beer
    0.60
     CAUSE
    0.60
    stock
    0.59
    تقاوى
    0.57
     chakra
    0.57
    Activations Density 0.233%

    No Known Activations