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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24-GEMMASCOPE-RES-16K
    6. 8173
    Prev
    Next
    INDEX
    Explanations

    code structure and data manipulation operations

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

    Code iterating through entries or iterators

    np_acts-logits-general · gemini-2.0-flash

    accessing collection elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +][
    -0.71
    AddHtmlAttribute
    -0.66
    はじめに
    -0.61
    awtextra
    -0.60
    InjectAttribute
    -0.58
    Décès
    -0.58
    licone
    -0.55
     defaultstate
    -0.55
    Спољашње
    -0.55
    UnknownFieldSet
    -0.54
    POSITIVE LOGITS
     bezeichneter
    0.69
     enumerate
    0.61
    entrySet
    0.60
    Iter
    0.60
    iter
    0.59
    GetEnumerator
    0.57
    iterate
    0.56
     Iterate
    0.56
    Iterable
    0.54
    values
    0.54
    Activations Density 0.120%

    No Known Activations