© 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. 6132
    Prev
    Next
    INDEX
    Explanations

    conditional statements and uncertainty in arguments or statements

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

    Beginning of conditional statements ("If you/we...")

    np_acts-logits-general · gemini-2.0-flash

    you/we do/think/consider

    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
    bootstrapcdn
    -0.81
     noqa
    -0.73
    protoimpl
    -0.71
    SharedCtor
    -0.70
    PreferredItem
    -0.69
     kasarigan
    -0.69
    GenerationType
    -0.69
    новниш
    -0.67
    RegistryLite
    -0.66
    +#+#
    -0.65
    POSITIVE LOGITS
     look
    1.54
     Look
    1.29
    Look
    1.28
    look
    1.25
     compare
    1.15
     looked
    1.14
     LOOK
    1.12
    LOOK
    1.10
     consider
    1.07
     looking
    0.99
    Activations Density 0.395%

    No Known Activations