© 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__L0-22
    6. 770
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 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
     propOrder
    -1.07
    ganu
    -1.02
     bezeichneter
    -1.01
     שוליים
    -0.96
     оригіналу
    -0.95
    enumii
    -0.94
    enderror
    -0.94
     MainAxisSize
    -0.93
     تانيه
    -0.93
     malheure
    -0.90
    POSITIVE LOGITS
     Light
    1.53
     LIGHT
    1.47
    Light
    1.47
    light
    1.44
     light
    1.40
    LIGHT
    1.34
    lights
    1.14
     Lightfoot
    1.13
     Lights
    1.11
    Lights
    1.10
    Activations Density 0.032%

    No Known Activations