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. 15-GEMMASCOPE-RES-16K
    6. 12938
    Prev
    Next
    INDEX
    Explanations

    statements and formal declarations made by individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.84
    StoryboardSegue
    -0.72
    ########.
    -0.69
    +:+
    -0.69
     Wiktionnaire
    -0.67
    хьтан
    -0.67
    клопе
    -0.67
    Xna
    -0.66
    تقاوى
    -0.65
    onViewCreated
    -0.65
    POSITIVE LOGITS
     wrote
    0.78
     written
    0.69
     letter
    0.65
     write
    0.61
     writes
    0.60
     statement
    0.56
    letter
    0.54
     notes
    0.53
     penned
    0.53
     tulis
    0.53
    Activations Density 0.127%

    No Known Activations