© 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. 11949
    Prev
    Next
    INDEX
    Explanations

    questions or inquiries regarding reasons and explanations

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

    "why" followed by a pronoun

    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 @ 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
    Them
    -0.58
     Cæsar
    -0.58
     vielä
    -0.56
     alfo
    -0.56
     Makefile
    -0.54
     Pelop
    -0.53
    Makefile
    -0.52
    stdc
    -0.52
    šak
    -0.50
     Roskov
    -0.49
    POSITIVE LOGITS
     we
    1.50
     they
    1.47
     there
    1.35
     the
    1.17
     it
    1.12
     you
    1.11
     he
    1.10
     someone
    0.94
     things
    0.92
     some
    0.92
    Activations Density 0.478%

    No Known Activations