© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 79
    Prev
    Next
    INDEX
    Explanations

    technical terms and code-related keywords

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

    Beginning of words after prefixes

    np_acts-logits-general · gemini-2.0-flash

    prefixes of multi-syllable words

    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
    NewUrlParser
    -1.22
    giène
    -0.92
    __*/
    -0.85
     InputDecoration
    -0.81
     Audiodateien
    -0.79
    écution
    -0.75
     ویکی‌پدیا
    -0.75
    $_['
    -0.74
     AssemblyCulture
    -0.73
     consultato
    -0.72
    POSITIVE LOGITS
    withstanding
    0.72
    sterious
    0.60
    aimana
    0.57
    licopter
    0.55
    adecimal
    0.54
    itudinal
    0.52
    thma
    0.50
    erdings
    0.49
    betical
    0.47
    adays
    0.47
    Activations Density 0.943%

    No Known Activations