Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3047
    Prev
    Next
    INDEX
    Explanations

    words related to causation and consequence in social or political contexts

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

    Follows forms of the verb "to be"

    np_acts-logits-general · gemini-2.0-flash

    forms of "to be" followed by descriptors

    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
     impactful
    -0.77
     incentiv
    -0.70
     showcasing
    -0.69
     leveraging
    -0.68
     standalone
    -0.67
     prioritizing
    -0.64
     prioritize
    -0.62
     prioritized
    -0.60
     showcased
    -0.58
     clunky
    -0.57
    POSITIVE LOGITS
     doubtless
    0.84
    faßt
    0.83
     muß
    0.78
     thence
    0.78
     daß
    0.75
     läßt
    0.73
     mußte
    0.73
     withal
    0.69
    SourceChecksum
    0.68
     mußten
    0.68
    Activations Density 0.720%

    No Known Activations