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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 9312
    Prev
    Next
    INDEX
    Explanations

    terms related to UI elements and image processing in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.65
    archiviato
    -0.57
     Bourgoin
    -0.56
    mycompany
    -0.55
    édrale
    -0.55
    itania
    -0.50
     Alt
    -0.50
    bleau
    -0.49
     Mal
    -0.49
    sizeCache
    -0.48
    POSITIVE LOGITS
    kháu
    0.81
     createContext
    0.69
    lu
    0.68
    ImageView
    0.67
     OnTriggerEnter
    0.63
    OutputStream
    0.60
     createSlice
    0.60
     BorderRadius
    0.59
    cshtml
    0.57
    __*/
    0.57
    Activations Density 2.178%

    No Known Activations