© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 13617
    Prev
    Next
    INDEX
    Explanations

    the phrase "a few" preceding various nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Slf
    -0.75
    לית
    -0.64
     tasche
    -0.61
     Bray
    -0.61
     esetén
    -0.61
    Berger
    -0.60
     laikā
    -0.59
    ᾶ
    -0.59
    퀀
    -0.59
     bolig
    -0.59
    POSITIVE LOGITS
     dozen
    1.27
     few
    1.11
    dozen
    1.11
     FEW
    1.08
    few
    1.02
     wenige
    1.00
     unknownFields
    0.95
     Few
    0.93
     wenigen
    0.92
     hundred
    0.91
    Activations Density 0.052%

    No Known Activations