© 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. 18-GEMMASCOPE-RES-16K
    11. 9606
    Prev
    Next
    INDEX
    Explanations

    expressions of confusion or the need for clarification regarding understanding various subjects

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

    Words/tokens followed by "why"

    np_acts-logits-general · gemini-2.0-flash

    asking why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calldata
    -0.69
     Roskov
    -0.66
    tagHelperRunner
    -0.58
    zielle
    -0.56
    Hauptartikel
    -0.55
    IsMutable
    -0.53
    bootstrapcdn
    -0.53
    IsContent
    -0.52
     <<<<<<<<<<<<<<
    -0.52
    richTextPanel
    -0.51
    POSITIVE LOGITS
     why
    2.70
    why
    2.29
     Why
    2.10
    Why
    2.05
     WHY
    1.95
     pourquoi
    1.89
    WHY
    1.87
     warum
    1.80
     waarom
    1.75
     Warum
    1.72
    Activations Density 0.481%

    No Known Activations