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

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 7051
    Prev
    Next
    INDEX
    Explanations

    phrases expressing responsibility and agency in social contexts

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

    Tokens preceding auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    pronoun followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ğından
    -0.60
    ceral
    -0.49
     Cube
    -0.47
     Lightroom
    -0.46
    ನ
    -0.46
     Bioaccumulative
    -0.46
    mingen
    -0.45
     nakalista
    -0.44
     Cus
    -0.43
    靖
    -0.43
    POSITIVE LOGITS
     throng
    0.69
     conni
    0.57
     equally
    0.55
     мәкал
    0.55
     troop
    0.53
    Rendered
    0.52
    Witam
    0.52
     rendered
    0.52
     narrated
    0.52
     render
    0.50
    Activations Density 0.073%

    No Known Activations