© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1284
    Prev
    Next
    INDEX
    Explanations

    references to technical specifications and plans

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

    phrases related to evaluation and interpretation of findings

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

    general trends and principles

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    rungsseite
    -0.85
    出版年
    -0.79
     kasarigan
    -0.71
     للمعارف
    -0.71
     通販
    -0.66
    )_/¯
    -0.64
    offsetof
    -0.63
    endphp
    -0.63
     Comprometido
    -0.61
    HtmlAttribute
    -0.61
    POSITIVE LOGITS
     general
    2.53
    general
    2.13
     generally
    1.85
     basic
    1.81
     generales
    1.72
     geral
    1.70
    General
    1.66
     generale
    1.66
     GENERAL
    1.66
    generally
    1.65
    Activations Density 0.701%

    No Known Activations