© 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. 22-GEMMASCOPE-RES-16K
    11. 3800
    Prev
    Next
    INDEX
    Explanations

    terms related to slowness, particularly in motion or actions

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

    "slow"

    np_acts-logits-general · gemini-2.0-flash

    slow adjectives for states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -0.62
    nodoc
    -0.59
    Hochspringen
    -0.57
    >");
    -0.56
     linkovi
    -0.56
     للاسماء
    -0.55
    ToBounds
    -0.55
     محفوظة
    -0.54
    )?;
    -0.54
    ɵɵelementEnd
    -0.54
    POSITIVE LOGITS
     Slow
    0.95
    Slow
    0.93
     slow
    0.85
     yavaş
    0.81
     SLOW
    0.80
     disambiguazione
    0.78
    slow
    0.77
    poke
    0.76
    SLOW
    0.70
     lenta
    0.69
    Activations Density 0.101%

    No Known Activations