© 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. 41-GEMMASCOPE-RES-16K
    6. 7321
    Prev
    Next
    INDEX
    Explanations

    elements related to structured data and metadata formats, such as JSON and schema definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .')
    -2.14
    .');
    -2.14
    ')
    
    -2.13
    '));
    
    -2.08
    ']);
    
    -2.06
    ');
    
    -2.06
    '])
    
    -2.06
     ')
    
    -2.02
    '))
    
    -2.00
    '),
    
    -1.98
    POSITIVE LOGITS
    setVerticalGroup
    0.45
    IntoConstraints
    0.43
     CreateTagHelper
    0.40
    ∙
    0.35
    ⁣
    0.35
     transfieras
    0.34
    шру
    0.34
    erías
    0.34
    äť
    0.32
    embolso
    0.31
    Activations Density 0.453%

    No Known Activations