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-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7449
    Prev
    Next
    INDEX
    Explanations

    specific terms related to programming or database entries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.61
    ########.
    -0.53
    +#+#
    -0.53
     الرياضيه
    -0.49
    таратура
    -0.49
     HasFactory
    -0.49
     BoxFit
    -0.48
    SharedCtor
    -0.48
    Ƚ
    -0.48
    хівовано
    -0.47
    POSITIVE LOGITS
    getOutputStream
    0.43
    SpringBootTest
    0.41
    RectangleBorder
    0.41
    InjectAttribute
    0.38
     dotyczące
    0.37
     怎样
    0.36
    coper
    0.36
     '{@
    0.36
     achtergrond
    0.35
     onOptions
    0.34
    Activations Density 2.038%

    No Known Activations