© 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. 9-GEMMASCOPE-RES-16K
    6. 279
    Prev
    Next
    INDEX
    Explanations

    specific references to awards and achievements related to various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.70
     Meksiku
    -0.69
    thâu
    -0.63
     umani
    -0.59
    initely
    -0.57
     متحده
    -0.55
     виправивши
    -0.54
    abetes
    -0.54
    didSet
    -0.53
     سكانية
    -0.53
    POSITIVE LOGITS
     InputDecoration
    0.88
    WebVitals
    0.83
     estimés
    0.73
    最快更新
    0.71
     ↓,
    0.70
    tiefel
    0.69
    Ifc
    0.69
    حوالہ
    0.69
     pleaſure
    0.68
    Rhestr
    0.68
    Activations Density 1.261%

    No Known Activations