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. 2950
    Prev
    Next
    INDEX
    Explanations

    structured elements and syntax in code or markup languages

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

    Text before a reference link

    np_acts-logits-general · gemini-2.0-flash

    linked references

    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
    migrationBuilder
    -0.64
    iastes
    -0.59
    cticut
    -0.56
    وصلات
    -0.55
    stens
    -0.54
    cookieParser
    -0.53
    tagext
    -0.53
     esternos
    -0.51
    WithIOException
    -0.50
    ✨:
    -0.49
    POSITIVE LOGITS
    HtmlAttribute
    0.65
    tvguidetime
    0.64
    卸
    0.59
     Roskov
    0.58
    devamını
    0.57
    InjectAttribute
    0.57
     IndexPath
    0.55
    <0xF3>
    0.54
    ConfigureAwait
    0.54
    enumi
    0.54
    Activations Density 0.137%

    No Known Activations