© 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 - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 464
    Prev
    Next
    INDEX
    Explanations

    patterns of usage related to the phrase "used to" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themſelves
    -0.70
    addPreferredGap
    -0.63
     ſtate
    -0.63
     himſelf
    -0.62
    windowFixed
    -0.62
    ſelves
    -0.62
     ſmall
    -0.60
    Hentet
    -0.60
    oustics
    -0.56
     ſever
    -0.56
    POSITIVE LOGITS
     früher
    0.81
     раньше
    0.79
    昔
    0.73
     formerly
    0.72
     vroeger
    0.71
    เคย
    0.70
     pernah
    0.69
     Formerly
    0.68
    GraphicsUnit
    0.67
    исленность
    0.65
    Activations Density 0.169%

    No Known Activations