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. 1735
    Prev
    Next
    INDEX
    Explanations

    indicators of text structure, specifically the beginning of a section or paragraph

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

    Non-English programming, filenames, or identifiers

    np_acts-logits-general · gemini-2.0-flash

    code constructs and dates

    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
     and
    -0.57
     new
    -0.53
     with
    -0.50
    الإنجليزية
    -0.49
     as
    -0.46
     when
    -0.46
    ously
    -0.45
    richTextPanel
    -0.43
     esquerdo
    -0.43
    <b>
    -0.43
    POSITIVE LOGITS
     Efq
    0.87
    roek
    0.77
    SuppressLint
    0.76
    <bos>
    0.69
    helves
    0.66
    UrlResolution
    0.65
     дописавши
    0.65
    évaluateur
    0.65
    CodeAnalysis
    0.64
    ")));
    
    0.64
    Activations Density 0.060%

    No Known Activations