© 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. 7-GEMMASCOPE-RES-16K
    6. 7913
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.79
    VERTISEMENT
    -0.76
     RSITY
    -0.75
     FontWeight
    -0.75
    CHREIB
    -0.72
     kits
    -0.71
    ENEFITS
    -0.71
    BorderFactory
    -0.69
    ghijklmnop
    -0.68
     ERSITY
    -0.68
    POSITIVE LOGITS
    ↵
    1.72
    ↵↵
    1.41
    <eos>
    1.34
    ↵↵↵
    1.18
    </tr>
    1.12
    ↵↵↵↵
    1.06
    ↵↵↵↵↵
    1.03
    [toxicity=0]
    0.98
    ↵↵↵↵↵↵
    0.96
    ↵↵↵↵↵↵↵
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.