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. 1-GEMMASCOPE-RES-16K
    6. 6245
    Prev
    Next
    INDEX
    Explanations

    terms related to Java Spring Framework components and repository patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cor
    -0.46
    Sti
    -0.43
     anak
    -0.43
     being
    -0.43
     –
    -0.43
    ons
    -0.43
     ?
    -0.42
     sich
    -0.42
     Kinder
    -0.42
     yang
    -0.42
    POSITIVE LOGITS
    MessageTagHelper
    0.93
     JpaRepository
    0.83
     onCancelled
    0.82
    IsMutable
    0.81
     المعيارى
    0.75
    bleed
    0.74
     bleeds
    0.73
     cursed
    0.73
    />";
    0.72
    cursed
    0.72
    Activations Density 2.211%

    No Known Activations