© 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. 9339
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or identifiers within structured data or code

    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
     Lovato
    -0.88
    ActivityCompat
    -0.86
    featureID
    -0.79
    ungal
    -0.76
     albicans
    -0.75
    ACHUSETTS
    -0.75
    Lois
    -0.74
    ญิง
    -0.74
    ofollow
    -0.73
    chtenstein
    -0.72
    POSITIVE LOGITS
     Syr
    0.78
    Basket
    0.75
     Schal
    0.74
     Turi
    0.69
     Gers
    0.68
    Insight
    0.68
     Syrians
    0.67
     Nicol
    0.67
    PROBLEM
    0.67
     Mezz
    0.66
    Activations Density 0.544%

    No Known Activations