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. 18-GEMMASCOPE-RES-16K
    6. 15385
    Prev
    Next
    INDEX
    Explanations

    elements related to control flow structures in programming

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

    Code related to indexing, especially in loops

    np_acts-logits-general · gemini-2.0-flash

    code index variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (!__
    -0.58
    ETHING
    -0.56
     ویکی‌پدیای
    -0.56
    Jîn
    -0.51
    afin
    -0.51
     فريبيس
    -0.51
     surla
    -0.50
     समीक्षाओं
    -0.50
    Tikang
    -0.50
    पया
    -0.49
    POSITIVE LOGITS
     index
    1.41
     Index
    1.31
    Index
    1.24
    index
    1.22
     INDEX
    1.16
    INDEX
    1.13
    索引
    1.09
     indices
    1.09
     Indexes
    1.06
     Indices
    1.05
    Activations Density 0.503%

    No Known Activations