© 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. 2-GEMMASCOPE-RES-16K
    6. 7921
    Prev
    Next
    INDEX
    Explanations

    formatted text elements such as mathematical symbols, figures, or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.65
     fact
    -0.35
    endphp
    -0.35
    品です
    -0.34
    ERES
    -0.34
     Edmund
    -0.34
    Còn
    -0.33
    Và
    -0.33
    espejo
    -0.32
    troppo
    -0.32
    POSITIVE LOGITS
    MigrationBuilder
    0.68
    WriteBarrier
    0.66
    AutoScaleMode
    0.61
    GEBURTSDATUM
    0.60
    
    0.59
     typelib
    0.58
     الرياضيه
    0.58
    OGND
    0.57
     defaultstate
    0.56
     Infórmanos
    0.56
    Activations Density 1.278%

    No Known Activations