© 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. 3-GEMMASCOPE-RES-16K
    6. 2366
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VERTISEMENT
    -0.78
     RSITY
    -0.71
    ſhip
    -0.70
    leſs
    -0.69
    initializeApp
    -0.69
     BorderRadius
    -0.68
    CHREIB
    -0.67
    ENEFITS
    -0.67
     FormsModule
    -0.66
     createSprite
    -0.65
    POSITIVE LOGITS
    ↵
    1.69
    <eos>
    1.33
    ↵↵
    1.32
    </tr>
    1.31
    ↵↵↵
    1.21
    ↵↵↵↵
    1.07
    [toxicity=0]
    1.03
    ↵↵↵↵↵
    1.01
    ↵↵↵↵↵↵
    0.96
    ↵↵↵↵↵↵↵
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.