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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3530
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to "dis" or "disc" indicating divisions, discriminations, and disorders

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

    starting with "Dis" or "disc"

    np_acts-logits-general · gemini-2.0-flash

    disparaging / disagreeing / discharging

    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
    abestanden
    -0.85
    WebVitals
    -0.73
    Panamoan
    -0.69
    PyExc
    -0.68
    duire
    -0.63
     препратки
    -0.63
    CGContext
    -0.62
     Alg
    -0.61
    LookAnd
    -0.61
    interopRequire
    -0.60
    POSITIVE LOGITS
     skimage
    0.62
     useDispatch
    0.62
     DIS
    0.58
    DIS
    0.57
     Réponses
    0.54
     Brü
    0.53
    DSC
    0.52
     Donc
    0.51
    ChildScrollView
    0.50
    Dis
    0.50
    Activations Density 0.200%

    No Known Activations