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. 10-GEMMASCOPE-RES-16K
    6. 3115
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and genealogical connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.75
     فريبيس
    -0.71
    InvalidProtocol
    -0.58
     Epile
    -0.58
    ToScroll
    -0.57
    LookAnd
    -0.56
    ametro
    -0.56
     <",
    -0.56
     وتسجيلات
    -0.55
    دانشنامهٔ
    -0.55
    POSITIVE LOGITS
    apimachinery
    0.51
     références
    0.49
    uated
    0.48
    lawayo
    0.46
    iedene
    0.46
    inqui
    0.46
    ngOnInit
    0.45
    طيع
    0.45
     Lozano
    0.45
    tiously
    0.45
    Activations Density 0.015%

    No Known Activations