© 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. 40-GEMMASCOPE-RES-16K
    6. 1854
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure elements used in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _'.$
    -0.58
    _"+
    -0.52
    _'+
    -0.47
    /#{
    -0.47
    -"+
    -0.47
     comfort
    -0.46
    /'.$
    -0.44
    ?』
    -0.42
     {}'.
    -0.42
    ?”,
    -0.41
    POSITIVE LOGITS
    EndGlobalSection
    0.45
    脚注の使い方
    0.43
    SuspendLayout
    0.40
     tryck
    0.38
    visející
    0.36
    </em>
    0.36
    oredCriteria
    0.36
     
    0.34
       
    0.34
     prisonniers
    0.34
    Activations Density 0.503%

    No Known Activations