Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6425
    Prev
    Next
    INDEX
    Explanations

    instances of the word "once" and its variations, indicating a focus on moments of change or significant actions

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

    Follows "once"

    np_acts-logits-general · gemini-2.0-flash

    temporal clauses starting with once

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    autogui
    -0.47
    LElement
    -0.46
     readiness
    -0.44
     جدًا
    -0.44
    seur
    -0.42
     good
    -0.42
    ├──
    -0.42
    feldt
    -0.42
    ppelin
    -0.41
    Precalculus
    -0.41
    POSITIVE LOGITS
    ValueStyle
    0.91
     MainAxisSize
    0.84
    دانشنامهٔ
    0.80
    NameInMap
    0.78
    uxxxx
    0.78
    fromnode
    0.73
    ContentAlignment
    0.70
     autorytatywna
    0.70
    IntoConstraints
    0.68
    Clik
    0.68
    Activations Density 0.260%

    No Known Activations