© 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. 12945
    Prev
    Next
    INDEX
    Explanations

    closing PHP tags

    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
     Exactos
    -0.38
     שול
    -0.38
    Dont
    -0.37
    getTop
    -0.36
     ModelExpression
    -0.36
     gyhoeddwyd
    -0.35
    setcounter
    -0.35
    xampp
    -0.35
    DataMember
    -0.35
     Bluffs
    -0.34
    POSITIVE LOGITS
     ?>
    1.40
    endphp
    1.22
     ?>
    
    1.16
    ?>
    1.14
    ?>
    
    1.08
     ?></
    0.98
    ;?>
    0.85
    {?>
    0.85
     {?>
    0.85
     ?>"
    0.84
    Activations Density 0.081%

    No Known Activations