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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 958
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to continuity and convergence in functional analysis

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

    mathematical continuity or compactness

    np_acts-logits-general · gemini-2.0-flash

    continuity, compactness, uniform properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    DockStyle
    -0.81
    MENAFN
    -0.49
     initComponents
    -0.46
     Tilt
    -0.44
     pinulongan
    -0.42
    stination
    -0.41
     TextInputType
    -0.41
    Quint
    -0.41
    FunctionFlags
    -0.40
    ConstraintMaker
    -0.40
    POSITIVE LOGITS
    GEBURTSDATUM
    0.50
     Italijanski
    0.39
     clínico
    0.38
    godic
    0.38
     ayı
    0.36
    lipas
    0.36
    expandindo
    0.35
     existence
    0.34
    forName
    0.34
     clinique
    0.33
    Activations Density 2.139%

    No Known Activations