© 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. 22-GEMMASCOPE-RES-16K
    6. 12651
    Prev
    Next
    INDEX
    Explanations

    quantitative and statistical terms related to models and expressions in research literature

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

    Tokens starting with "mar" (case-insensitive)

    np_acts-logits-general · gemini-2.0-flash

    MARCO or marginal

    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
     Huey
    -0.56
     Baldwin
    -0.54
    出版年
    -0.53
    UrlResolution
    -0.53
     Pudding
    -0.53
    脚注の使い方
    -0.52
     Pelham
    -0.52
     Aya
    -0.52
     Hilo
    -0.51
     NOD
    -0.50
    POSITIVE LOGITS
     MAR
    2.48
    MAR
    2.35
     Мар
    2.22
     mar
    2.19
     Mar
    2.16
    Mar
    2.13
    Мар
    2.05
    mar
    2.03
     MARK
    2.02
     Mark
    1.99
    Activations Density 0.305%

    No Known Activations