© 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. 10-GEMMASCOPE-RES-16K
    6. 8343
    Prev
    Next
    INDEX
    Explanations

    references to additional considerations or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.84
    IVEREF
    -0.65
    abestanden
    -0.63
    ViewImports
    -0.60
    initComponents
    -0.59
    EDEFAULT
    -0.57
    httphttps
    -0.57
    انيف
    -0.55
    anneer
    -0.54
    الإنجليزية
    -0.53
    POSITIVE LOGITS
    そもそも
    0.89
    何より
    0.64
    lack
    0.53
     lack
    0.53
    更何况
    0.52
    何况
    0.49
     disproportion
    0.48
    తు
    0.48
     overkill
    0.47
     blatantly
    0.47
    Activations Density 0.511%

    No Known Activations