© 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. 5941
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negative evaluations or criticisms

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

    Follows intensifiers like "more", "most", or "really"

    np_acts-logits-general · gemini-2.0-flash

    more interesting/surprising/concerning

    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
    ArgumentParser
    -0.84
    جغرافيا
    -0.76
    épendance
    -0.75
    MigrationBuilder
    -0.74
     ModelExpression
    -0.74
     resourceCulture
    -0.71
    HtmlAttribute
    -0.71
    ValueStyle
    -0.70
     виправивши
    -0.70
    хьтан
    -0.69
    POSITIVE LOGITS
     interesting
    1.76
     fascinating
    1.70
     intriguing
    1.62
     alarming
    1.58
     surprising
    1.54
     frightening
    1.52
     disturbing
    1.49
     astonishing
    1.48
     startling
    1.48
    interesting
    1.48
    Activations Density 0.561%

    No Known Activations