© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14979
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "of"

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

    "Of course" or "of late"

    np_acts-logits-general · gemini-2.0-flash

    of course

    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
    they
    -0.60
    /
    -0.57
    //
    -0.57
    They
    -0.54
    คุณ
    -0.53
     invitamos
    -0.52
    and
    -0.51
    ist
    -0.48
     они
    -0.48
     illustrazione
    -0.48
    POSITIVE LOGITS
     sorts
    1.34
     course
    1.31
    course
    1.16
    COURSE
    1.06
     the
    0.99
    sted
    0.95
    renda
    0.94
     yore
    0.93
     COURSE
    0.92
     our
    0.91
    Activations Density 1.589%

    No Known Activations