Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 8166
    Prev
    Next
    INDEX
    Explanations

    topics related to advanced technology and its applications in various scientific fields

    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
    روف
    -0.43
    greif
    -0.40
    geable
    -0.39
    rigin
    -0.38
     βά
    -0.38
     ajutor
    -0.36
     depic
    -0.36
     ense
    -0.35
     ErrIntOverflow
    -0.35
    each
    -0.35
    POSITIVE LOGITS
     nahilalakip
    0.93
     estimés
    0.83
    tvguidetime
    0.79
     Meksiku
    0.78
    Ārējās
    0.77
    LookAnd
    0.73
     חיצוניים
    0.73
    SharedDtor
    0.73
    İstinadlar
    0.73
    Personensuche
    0.72
    Activations Density 1.202%

    No Known Activations