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. 227
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and attributes related to code structure and programming concepts

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

    substrings commonly used in coding or technical contexts, such as abbreviations or specific file extensions.

    oai_token-act-pair · gpt-4oTriggered 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
    basicConfig
    -0.73
    multer
    -0.69
    BASELINE
    -0.67
    Activité
    -0.56
    onAttach
    -0.54
     doubtnut
    -0.51
    urfs
    -0.51
    انگلیسی
    -0.51
    LogFactory
    -0.49
    Evet
    -0.48
    POSITIVE LOGITS
     كومونز
    0.64
    PhysRev
    0.61
     Moun
    0.61
    ListComponent
    0.58
     ligh
    0.57
     onAnimation
    0.56
    \]
    0.56
     getF
    0.56
     Trou
    0.55
     виправивши
    0.55
    Activations Density 0.946%

    No Known Activations