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. 16-GEMMASCOPE-RES-16K
    6. 15023
    Prev
    Next
    INDEX
    Explanations

    references to organizational structures and events related to discussions, panels, and forums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    before "in," "of," or "and"

    np_acts-logits-general · gemini-2.0-flash

    organized events and initiatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.73
    onedDateTime
    -0.70
     estekak
    -0.62
     AssemblyTitle
    -0.59
    aarrggbb
    -0.58
    nitus
    -0.57
     useState
    -0.56
     ddelweddau
    -0.55
    thâu
    -0.55
     يتيمه
    -0.54
    POSITIVE LOGITS
    といって
    0.64
    MemoryWarning
    0.63
    providedIn
    0.62
    と呼ばれる
    0.61
    WebServlet
    0.56
    ™
    0.56
     Series
    0.52
     concept
    0.52
    と言って
    0.51
     Corollary
    0.51
    Activations Density 0.419%

    No Known Activations