© 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. 23-GEMMASCOPE-RES-16K
    6. 6540
    Prev
    Next
    INDEX
    Explanations

    descriptions of high-tech watch features and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kháu
    -0.74
    Manbalar
    -0.67
    ViewFeatures
    -0.62
     AssemblyProduct
    -0.62
    MLLoader
    -0.61
    WebServlet
    -0.60
     AssemblyTitle
    -0.60
     kaynağından
    -0.59
     protoimpl
    -0.59
    endphp
    -0.58
    POSITIVE LOGITS
     watch
    2.06
     watches
    1.87
    watch
    1.69
     Watch
    1.67
    Watch
    1.55
    watches
    1.52
     WATCH
    1.48
     Watches
    1.47
    WATCH
    1.31
     wrist
    1.22
    Activations Density 0.063%

    No Known Activations