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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 1798
    Prev
    Next
    INDEX
    Explanations

    content related to planning or organizing events and tasks

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

    preceding verbs like "get" or "got"

    np_acts-logits-general · gemini-2.0-flash

    get it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aanwezig
    -0.48
    ShouldBe
    -0.48
     vorhanden
    -0.44
     Artik
    -0.44
     olev
    -0.43
    obec
    -0.43
     willkommen
    -0.43
     blevet
    -0.43
     zich
    -0.43
    eira
    -0.42
    POSITIVE LOGITS
    MessageOf
    0.86
    yntaxException
    0.86
    AndEndTag
    0.83
     AssemblyCulture
    0.83
    DockStyle
    0.82
    ///</
    0.81
     aika
    0.78
    SharedDtor
    0.77
    principalTable
    0.76
     "..\..\..\
    0.75
    Activations Density 0.146%

    No Known Activations