© 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. 11301
    Prev
    Next
    INDEX
    Explanations

    integers and numbers in different formats

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

    Tokens followed by a digit

    np_acts-logits-general · gemini-2.0-flash

    technical and programming language

    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
     nakalista
    -0.78
     studio
    -0.73
     workshop
    -0.61
    studio
    -0.60
     estúdio
    -0.60
     studios
    -0.58
    workshop
    -0.56
     study
    -0.55
     WORKSHOP
    -0.55
     Estudio
    -0.55
    POSITIVE LOGITS
    GEBURTSDATUM
    0.59
     ویکی‌پدیای
    0.55
     insuffisamment
    0.54
    LEncoder
    0.54
    testens
    0.53
    ChildScrollView
    0.53
     дописавши
    0.52
     Вікіпе
    0.52
    lapsingToolbar
    0.51
    MLLoader
    0.51
    Activations Density 0.526%

    No Known Activations