© 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. 15-GEMMASCOPE-RES-16K
    6. 6397
    Prev
    Next
    INDEX
    Explanations

    instances of emphasis or highlighting of contrasts in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rosalie
    -0.84
     PublicKey
    -0.82
     Amalia
    -0.78
     BoxDecoration
    -0.77
     DRM
    -0.76
     Celia
    -0.76
     Rigidbody
    -0.75
     wikipagina
    -0.74
     AIS
    -0.74
    MSD
    -0.74
    POSITIVE LOGITS
     even
    1.10
     though
    1.00
     EVEN
    0.99
     Even
    0.98
    even
    0.94
    Even
    0.91
    though
    0.81
    Though
    0.80
    EVEN
    0.79
     Though
    0.78
    Activations Density 0.060%

    No Known Activations