© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 6243
    Prev
    Next
    INDEX
    Explanations

    JavaScript methods and functions used for selecting and manipulating elements in the document object model (DOM)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.70
     للاسماء
    -0.64
    发表于
    -0.59
    PushMatrix
    -0.59
     astore
    -0.59
    횟
    -0.58
    orsese
    -0.57
    googleapis
    -0.56
    yargs
    -0.55
    iVar
    -0.55
    POSITIVE LOGITS
    querySelector
    1.17
    querySelectorAll
    1.06
    getElementsBy
    0.67
     sī
    0.65
    érial
    0.61
     مواليد
    0.60
    ^(@)
    0.58
    $("
    0.58
    reinterpret
    0.57
    ख्य
    0.57
    Activations Density 0.030%

    No Known Activations