Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 4744
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and relationships in the context of formal proofs

    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
    Bibliographie
    -0.57
    Filmographie
    -0.56
    ENZA
    -0.52
     sắc
    -0.52
    )}</
    -0.52
    GeneratedMessage
    -0.52
    setVerticalGroup
    -0.51
    DropTable
    -0.50
    uría
    -0.50
    itemBuilder
    -0.50
    POSITIVE LOGITS
     OFDb
    0.79
     يتيمه
    0.78
     فريبيس
    0.68
    ArgsConstructor
    0.67
    LookAnd
    0.64
    IUrlHelper
    0.63
    OGND
    0.61
     ويكيپيديا
    0.58
    -------
    0.58
     himo
    0.57
    Activations Density 0.848%

    No Known Activations