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. 16-GEMMASCOPE-RES-16K
    6. 11987
    Prev
    Next
    INDEX
    Explanations

    usage of quotation marks and similar punctuation in text

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

    Code within strings and quotes

    np_acts-logits-general · gemini-2.0-flash

    code formatting

    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
    ../../
    -0.65
    ../
    -0.61
    ForKey
    -0.55
     getInt
    -0.55
     ERSITY
    -0.54
    └──
    -0.54
    度的
    -0.54
     hoek
    -0.53
    erial
    -0.53
    biele
    -0.53
    POSITIVE LOGITS
     disponibilités
    0.76
    MessageTagHelper
    0.75
     StringTokenizer
    0.74
    IntoConstraints
    0.69
    ArrowToggle
    0.69
    vode
    0.68
    GEBURTS
    0.67
    styleType
    0.67
     وتسجيلات
    0.65
    клопе
    0.65
    Activations Density 0.066%

    No Known Activations