© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13122
    Prev
    Next
    INDEX
    Explanations

    sentences that express obligations or requirements

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

    Follows "to" and precedes a verb implying avoidance

    np_acts-logits-general · gemini-2.0-flash

    to avoid effort/cost

    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
    DockStyle
    -0.70
    UrlResolution
    -0.69
    ніципалі
    -0.66
    Portale
    -0.64
     ExecuteAsync
    -0.64
     Roskov
    -0.62
    Hentet
    -0.60
    出版年
    -0.60
    RegistryLite
    -0.58
     ostavi
    -0.57
    POSITIVE LOGITS
     needlessly
    1.18
     unnecessarily
    1.16
     costly
    1.15
     unnecessary
    1.14
     wasteful
    1.13
     wasted
    1.11
     expensive
    1.11
     cumbersome
    1.10
     wasting
    1.09
     tedious
    1.09
    Activations Density 0.605%

    No Known Activations