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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2232
    Prev
    Next
    INDEX
    Explanations

    elements of SVG (Scalable Vector Graphics) path data and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mármol
    -0.36
    lemény
    -0.33
     estaciones
    -0.33
     conmigo
    -0.33
     cejas
    -0.32
     obicei
    -0.32
     îna
    -0.31
     solche
    -0.31
     encaje
    -0.30
     siguientes
    -0.29
    POSITIVE LOGITS
    awtextra
    1.29
    TagMode
    0.94
    inSlope
    0.82
    viewBox
    0.81
    makeConstraints
    0.79
    DIPSETTING
    0.78
    SequentialGroup
    0.77
    CppMethod
    0.77
    SizeF
    0.77
    kháu
    0.76
    Activations Density 0.225%

    No Known Activations