© 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. 15318
    Prev
    Next
    INDEX
    Explanations

    elements related to text formatting and styling in code

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

    The token "text" followed by punctuation or formatting

    np_acts-logits-general · gemini-2.0-flash

    text

    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
    withIdentifier
    -0.82
     AssemblyCompany
    -0.73
    Bronnen
    -0.68
    OGND
    -0.68
    DockStyle
    -0.68
     <=",
    -0.67
    Šaltiniai
    -0.67
    DeleteBehavior
    -0.66
    Παραπομπές
    -0.66
    Viited
    -0.64
    POSITIVE LOGITS
     text
    0.54
    ured
    0.53
    text
    0.52
     Utf
    0.52
     Text
    0.52
     asci
    0.47
    Text
    0.47
    TEXT
    0.47
     tek
    0.46
     TEXT
    0.46
    Activations Density 0.052%

    No Known Activations