© 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. 11946
    Prev
    Next
    INDEX
    Explanations

    technical or functional parameters in a structured format

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

    Unusual punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    news or event headlines

    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
    ressee
    -0.76
    UnknownFieldSet
    -0.65
     distanciation
    -0.65
     Parigi
    -0.64
     Rigidbody
    -0.63
     Jérusalem
    -0.60
     CURIAM
    -0.60
    forChild
    -0.58
     pardoned
    -0.58
     AllAfrica
    -0.56
    POSITIVE LOGITS
     betweenstory
    0.65
    日閲覧
    0.55
    wapV
    0.50
     Италијани
    0.48
    Palmar
    0.47
    ValueStyle
    0.46
    liau
    0.46
     Cost
    0.46
    데
    0.46
     Method
    0.45
    Activations Density 0.159%

    No Known Activations