© 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. 24-GEMMASCOPE-RES-16K
    11. 4170
    Prev
    Next
    INDEX
    Explanations

    instances of the word "once" and its variations emphasizing repetition or habitual actions

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

    Follows the word "Once"

    np_acts-logits-general · gemini-2.0-flash

    once again or upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    حياته
    -0.64
     morire
    -0.57
    unnitel
    -0.56
     tantôt
    -0.55
    /**
    -0.54
    marvin
    -0.51
    hline
    -0.50
    äldrar
    -0.49
     planète
    -0.48
    sinki
    -0.47
    POSITIVE LOGITS
     again
    1.20
     upon
    1.00
    again
    0.88
    Again
    0.87
     bitten
    0.85
     Upon
    0.85
     Again
    0.81
     UPON
    0.81
    upon
    0.76
    Upon
    0.73
    Activations Density 0.039%

    No Known Activations