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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 15832
    Prev
    Next
    INDEX
    Explanations

    the word "of" in various contexts

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

    "of course" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    of course, sorts

    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
    argout
    -0.62
     and
    -0.62
    /
    -0.60
    TypedDataSet
    -0.60
    ,
    -0.60
    คุณ
    -0.57
     invitamos
    -0.56
     or
    -0.54
     مرئيه
    -0.54
     to
    -0.53
    POSITIVE LOGITS
     course
    1.36
     sorts
    1.22
    course
    1.20
     yore
    0.97
    COURSE
    0.92
     COURSE
    0.86
     interest
    0.84
    renda
    0.84
    Course
    0.84
     Course
    0.83
    Activations Density 1.485%

    No Known Activations