© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 847
    Prev
    Next
    INDEX
    Explanations

    instances of numeric data or figures

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

    Numbers with zeros

    np_acts-logits-general · gemini-2.0-flash

    phone numbers 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
    classmethod
    -0.63
    ANGEL
    -0.59
    儿
    -0.59
     very
    -0.58
    ı
    -0.58
    ments
    -0.57
     واس
    -0.56
    est
    -0.56
    сть
    -0.56
     present
    -0.56
    POSITIVE LOGITS
    AndEndTag
    1.18
    0
    1.10
    awtextra
    0.93
    webElementXpaths
    0.85
    AddTagHelper
    0.83
     חיצוניים
    0.81
    +#+#
    0.81
     defaultstate
    0.80
    RegressionTest
    0.74
    vician
    0.73
    Activations Density 1.070%

    No Known Activations