© 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. 20-GEMMASCOPE-RES-16K
    11. 6998
    Prev
    Next
    INDEX
    Explanations

    phrases indicating frequency or habitual actions

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

    "Often" followed by related words

    np_acts-logits-general · gemini-2.0-flash

    often times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.69
     ​​
    -0.66
    intellij
    -0.63
    shadowOffset
    -0.59
     sempre
    -0.57
    eventually
    -0.55
    IsInitialized
    -0.55
    AnimationsModule
    -0.54
    Eloquent
    -0.54
    始终
    -0.53
    POSITIVE LOGITS
     times
    1.52
    times
    1.39
     TIMES
    1.02
    Times
    0.99
     veces
    0.97
     бывает
    0.93
     Times
    0.88
     vezes
    0.85
     genug
    0.84
    TIMES
    0.84
    Activations Density 0.093%

    No Known Activations