© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4006
    Prev
    Next
    INDEX
    Explanations

    content related to news articles and summaries

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

    Tokens preceding page numbers or boxes

    np_acts-logits-general · gemini-2.0-flash

    box below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.92
     дописавши
    -0.77
     AssemblyTitle
    -0.75
    ########.
    -0.74
    UnknownFields
    -0.73
    ftagPool
    -0.70
    RectangleBorder
    -0.69
     AssemblyCompany
    -0.69
     CreateTagHelper
    -0.69
     AssemblyProduct
    -0.68
    POSITIVE LOGITS
     page
    1.06
     pages
    0.94
    page
    0.89
     Page
    0.82
    Page
    0.80
     panel
    0.80
    pages
    0.78
     inset
    0.76
     panels
    0.76
    opposite
    0.75
    Activations Density 0.788%

    No Known Activations