© 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. 0-GEMMASCOPE-RES-16K
    11. 2708
    Prev
    Next
    INDEX
    Explanations

    instances of the word "breaking" and its variations, often in the context of significant events or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )->
    -0.35
     zentralen
    -0.34
     mármol
    -0.32
     kwaliteit
    -0.31
     bedoeld
    -0.31
     lecz
    -0.31
     Vielfalt
    -0.31
     Vertreter
    -0.31
     AssemblyTitle
    -0.31
     temas
    -0.30
    POSITIVE LOGITS
     breaking
    2.53
     break
    2.39
     Breaking
    2.28
     breaks
    2.27
     broke
    2.27
     broken
    2.25
     Break
    2.23
    Breaking
    2.23
    breaking
    2.23
    break
    2.16
    Activations Density 0.254%

    No Known Activations