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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 13-GEMMASCOPE-RES-16K
    6. 10063
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to graphs or nodes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    This neuron activates on highly structured technical text, especially LaTeX-style math/diagram syntax and code-like test identifiers with dense brackets, braces, operators, and numeric parameters.

    oai_token-act-pair · gpt-5Triggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enllaços
    -0.68
    ArgsConstructor
    -0.64
    AndEndTag
    -0.63
    TintMode
    -0.58
    tonsoft
    -0.58
    SpringRunner
    -0.57
    UnknownFieldSet
    -0.57
    parsedMessage
    -0.57
    DockStyle
    -0.56
     Wikimedijinoj
    -0.56
    POSITIVE LOGITS
     estimés
    0.73
    aarrggbb
    0.63
     arşivlendi
    0.59
     ErrIntOverflow
    0.58
     henvis
    0.53
     otomatig
    0.53
    deleteById
    0.53
     pengertian
    0.51
    (")");
    0.49
    UTA
    0.48
    Activations Density 1.358%

    No Known Activations