© 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. 553
    Prev
    Next
    INDEX
    Explanations

    mentions of sporting events or competitions

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

    references to athletic accomplishments and milestones in sports

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

    advancing and elimination

    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
     sol
    -0.42
    Legături
    -0.41
     campionato
    -0.41
    Sol
    -0.39
    inau
    -0.38
    csp
    -0.38
    --;
    -0.37
    ignants
    -0.37
    phism
    -0.37
    genic
    -0.37
    POSITIVE LOGITS
     advancing
    1.26
     advance
    1.20
     advancement
    1.20
    advance
    1.11
     elimination
    1.10
     advanced
    1.09
     Advance
    1.09
    Advance
    1.05
     ADVANCE
    1.04
     advances
    1.01
    Activations Density 0.046%

    No Known Activations