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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 15689
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate player evaluation and performance comparisons in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     которое
    -0.66
    themselves
    -0.62
    ljeno
    -0.57
    uteen
    -0.56
    それぞれの
    -0.55
    それぞれ
    -0.55
    romptu
    -0.54
    omorphisms
    -0.53
    といけない
    -0.53
     яке
    -0.52
    POSITIVE LOGITS
     unlike
    0.72
     Known
    0.72
    Known
    0.70
    unlike
    0.68
     Unlike
    0.67
     possessing
    0.67
     capable
    0.66
     Compared
    0.66
    Unlike
    0.66
     capaz
    0.65
    Activations Density 0.218%

    No Known Activations