© 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. 21-GEMMASCOPE-RES-16K
    11. 14888
    Prev
    Next
    INDEX
    Explanations

    timestamps and duration references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.76
     समीक्षाओं
    -0.66
     المعيارى
    -0.65
    туа
    -0.60
     Roumanie
    -0.59
    verbs
    -0.58
    énario
    -0.58
    jspx
    -0.58
    quelize
    -0.58
     snippetHide
    -0.55
    POSITIVE LOGITS
     counted
    0.72
     sejak
    0.68
     since
    0.67
     after
    0.65
     calendriers
    0.62
    부터
    0.59
     post
    0.58
     desde
    0.58
     compter
    0.57
     counting
    0.57
    Activations Density 0.433%

    No Known Activations