© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3406
    Prev
    Next
    INDEX
    Explanations

    mentions of player statistics and performance in sports

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

    its followed by ordinal numbers

    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
     once
    -1.26
    once
    -1.18
    Once
    -1.14
     Once
    -1.09
     forever
    -1.04
     ONCE
    -1.00
    ONCE
    -0.93
     Forever
    -0.92
     einmal
    -0.85
     FOREVER
    -0.84
    POSITIVE LOGITS
     ninth
    1.19
     eighth
    1.13
     seventh
    1.12
     tenth
    1.10
     eleventh
    1.06
     twelfth
    1.04
     thirteenth
    1.03
     fourteenth
    1.02
     sixth
    0.97
     fifteenth
    0.93
    Activations Density 0.090%

    No Known Activations