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. 54
    Prev
    Next
    INDEX
    Explanations

    references to firms and films

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

    "firm" or "film"

    np_acts-logits-general · gemini-2.0-flash

    firm and film

    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
    a
    -0.84
    e
    -0.84
    o
    -0.80
    amaz
    -0.70
    awe
    -0.70
    eche
    -0.67
    ectomy
    -0.64
    Okey
    -0.61
     myeloma
    -0.61
    ा
    -0.61
    POSITIVE LOGITS
     pageContext
    0.87
    UIControlState
    0.86
    mable
    0.72
    stdafx
    0.67
    ngiliz
    0.66
    которые
    0.65
     Gump
    0.65
     okuyayım
    0.64
    WindowConstants
    0.64
     jLabel
    0.60
    Activations Density 0.129%

    No Known Activations