© 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. 8976
    Prev
    Next
    INDEX
    Explanations

    contexts related to "off" in various forms and combinations, especially in regard to actions or states of ceasing or separation

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

    The token "off" and its capitalization variants

    np_acts-logits-general · gemini-2.0-flash

    off- prefix

    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
     صوتيه
    -0.77
     textStatus
    -0.76
     resourceCulture
    -0.73
    Personendaten
    -0.73
    Portale
    -0.73
    :✨
    -0.69
    ioutil
    -0.68
    Życiorys
    -0.66
    هما
    -0.66
     Erskine
    -0.64
    POSITIVE LOGITS
     Off
    1.19
    Off
    1.08
     OFF
    1.07
     off
    1.04
    off
    1.01
    OFF
    0.93
    offs
    0.83
     offs
    0.73
     kil
    0.64
    Limits
    0.63
    Activations Density 0.076%

    No Known Activations