© 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. 22-GEMMASCOPE-RES-16K
    11. 11243
    Prev
    Next
    INDEX
    Explanations

    HTML table structures and elements

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

    Comes before symbols or formatting tokens

    np_acts-logits-general · gemini-2.0-flash

    error messages or logs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    rungsseite
    -0.49
    SizeMode
    -0.48
     sifat
    -0.46
     Gar
    -0.46
     Solano
    -0.44
    AutoField
    -0.43
    pipeline
    -0.43
    digest
    -0.43
    crose
    -0.43
    POSITIVE LOGITS
    <th>
    1.29
    <u>
    0.84
    SequentialGroup
    0.74
    Tembelea
    0.70
     nahilalakip
    0.68
    InputBorder
    0.67
    <h4>
    0.66
    WithIOException
    0.62
    щин
    0.60
    0.59
    Activations Density 0.032%

    No Known Activations