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. 14-GEMMASCOPE-RES-16K
    6. 9872
    Prev
    Next
    INDEX
    Explanations

    keywords related to decision-making and risk management in veterinary and emergency health contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hurry
    -0.54
     sympathize
    -0.54
    WebpackPlugin
    -0.53
     scorn
    -0.52
     مرئيه
    -0.52
    Rè
    -0.52
    urus
    -0.51
    ⓧ
    -0.51
     McGuire
    -0.51
    ográficos
    -0.51
    POSITIVE LOGITS
    égard
    0.61
     تضيفلها
    0.59
    related
    0.59
    relevant
    0.59
     related
    0.59
     gitara
    0.58
    GOTREF
    0.58
    يكب
    0.57
     flows
    0.57
     services
    0.56
    Activations Density 0.391%

    No Known Activations