© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 7025
    Prev
    Next
    INDEX
    Explanations

    conditional statements and flow control structures in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.61
    ArrowToggle
    -0.53
    олові
    -0.52
    EDEFAULT
    -0.47
    Citiți
    -0.44
    limin
    -0.43
     verlo
    -0.42
    ioso
    -0.42
     공식
    -0.42
    خواندن
    -0.41
    POSITIVE LOGITS
    ViewFeatures
    0.72
    tagHelperRunner
    0.65
     !
    0.64
     محفوظة
    0.61
    seamnă
    0.59
    ној
    0.55
    WriteLiteral
    0.55
    WebServlet
    0.54
    GeoNames
    0.52
     !'
    0.52
    Activations Density 0.091%

    No Known Activations