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. 0-GEMMASCOPE-RES-16K
    6. 2771
    Prev
    Next
    INDEX
    Explanations

    terms related to jumping or discontinuities in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sementara
    -0.34
     cintur
    -0.32
     straight
    -0.32
     Lingkungan
    -0.31
    RenderTarget
    -0.31
     MECHANICAL
    -0.31
     Affaires
    -0.31
     presidencial
    -0.31
     känner
    -0.30
     guarantees
    -0.30
    POSITIVE LOGITS
     jumps
    0.96
     Jumps
    0.85
     Walks
    0.79
     مرئيه
    0.74
     hops
    0.74
    jumps
    0.73
     ticks
    0.70
     Moves
    0.69
     glides
    0.67
     moves
    0.67
    Activations Density 1.818%

    No Known Activations