© 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. 1316
    Prev
    Next
    INDEX
    Explanations

    specialized scientific terms and symbols from mathematical or technical contexts

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

    HTML or code-related syntax

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

    sampling due to

    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
    ,
    -0.73
     y
    -0.72
     D
    -0.72
     met
    -0.72
     m
    -0.70
     de
    -0.70
     mit
    -0.69
     a
    -0.68
     M
    -0.68
     van
    -0.67
    POSITIVE LOGITS
     itſelf
    1.36
     auffi
    1.11
     ་་
    1.09
     doubtnut
    1.08
     photolibrary
    1.04
     myſelf
    1.03
     raiſ
    1.02
     Shakspeare
    1.01
     uſed
    0.99
     ſtill
    0.96
    Activations Density 0.019%

    No Known Activations