© 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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2335
    Prev
    Next
    INDEX
    Explanations

    equations or expressions involving assignments and operations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "):
    
    -0.86
    awtextra
    -0.81
     Duran
    -0.79
    "</
    -0.79
     endblock
    -0.78
    ContextCompat
    -0.74
     —
    -0.72
    ']);
    
    -0.72
     FontWeight
    -0.70
    '])
    
    -0.70
    POSITIVE LOGITS
     malade
    0.90
     dedans
    0.90
     Romains
    0.87
     doré
    0.85
     färg
    0.85
     nød
    0.84
     tremp
    0.83
     purpoſe
    0.83
     pleaſure
    0.82
     CBR
    0.81
    Activations Density 0.296%

    No Known Activations