© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13236
    Prev
    Next
    INDEX
    Explanations

    terms related to fasteners or clips

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.39
    netinet
    -0.38
     vit
    -0.37
     }}">
    -0.35
     motion
    -0.35
     nar
    -0.33
     Rh
    -0.32
     boo
    -0.32
    Билгалдахарш
    -0.30
    êng
    -0.29
    POSITIVE LOGITS
     clip
    2.02
     clipped
    1.95
     clipping
    1.91
     clips
    1.87
     Clip
    1.83
    Clip
    1.72
     Clips
    1.70
    clip
    1.66
     CLIP
    1.56
    Clips
    1.53
    Activations Density 0.453%

    No Known Activations