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. 11-GEMMASCOPE-RES-16K
    6. 13968
    Prev
    Next
    INDEX
    Explanations

    specific code syntax, particularly related to function calls and assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rub
    -0.63
    ters
    -0.62
     rich
    -0.61
     Zer
    -0.57
    في
    -0.57
    AndGet
    -0.56
     smart
    -0.55
     Sans
    -0.54
     Daz
    -0.54
    es
    -0.52
    POSITIVE LOGITS
    “…”
    0.94
    الدراسه
    0.86
    =\""
    0.85
     ainfi
    0.83
     Tacitus
    0.79
     وتسجيلات
    0.79
     horaire
    0.78
     auffi
    0.78
     distanciation
    0.77
    VIAF
    0.77
    Activations Density 0.078%

    No Known Activations