© 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. 11-GEMMASCOPE-RES-16K
    6. 4580
    Prev
    Next
    INDEX
    Explanations

    equations and terms related to mathematical or physical expressions in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.85
    webElementXpaths
    -0.78
     CanadaChoose
    -0.74
    Попис
    -0.71
    ագրություններ
    -0.71
    orne
    -0.70
    tangentMode
    -0.69
    PreInfinity
    -0.68
     ApiException
    -0.68
     OMIT
    -0.66
    POSITIVE LOGITS
     }^{
    0.59
     $^{\
    0.59
    ัจ
    0.58
     åp
    0.56
    页面存档备份
    0.56
    CDCl
    0.56
     $^{
    0.55
     $_{\
    0.55
    asyarakat
    0.55
    binaan
    0.55
    Activations Density 0.295%

    No Known Activations