Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2281
    Prev
    Next
    INDEX
    Explanations

    instances of significant player actions and performance metrics in sports narratives

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

    Followed by a past-tense verb

    np_acts-logits-general · gemini-2.0-flash

    past state or outcome

    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
     conci
    -0.51
    Generated
    -0.49
    Rhestr
    -0.49
    ofus
    -0.49
     useCallback
    -0.49
    วะ
    -0.48
    potranspiration
    -0.48
    kamers
    -0.48
    ifred
    -0.48
    (;;)
    -0.47
    POSITIVE LOGITS
    :✨
    0.66
    UnusedPrivate
    0.65
    webElementXpaths
    0.64
    tvguidetime
    0.63
    styleType
    0.60
    ГЛА
    0.55
    ifikant
    0.54
    MLLoader
    0.52
     noten
    0.52
     TextAppearance
    0.51
    Activations Density 0.122%

    No Known Activations