© 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. 3-GEMMASCOPE-RES-16K
    11. 8118
    Prev
    Next
    INDEX
    Explanations

    terms related to knowledge or recognition of notable people, places, or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estimés
    -0.56
    rungsseite
    -0.52
     sogget
    -0.52
    Tikang
    -0.50
    WebVitals
    -0.49
     φύ
    -0.49
    لينكات
    -0.48
    éndolo
    -0.48
     Numerology
    -0.47
     geliyor
    -0.46
    POSITIVE LOGITS
    Skocz
    0.68
     XNUMX
    0.67
     noDo
    0.66
     مشارکت‌کنندگان
    0.66
     poffible
    0.66
     greateſt
    0.65
     Jefus
    0.63
    ()",
    0.62
    brainly
    0.62
    ]--;
    0.62
    Activations Density 0.432%

    No Known Activations