© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 11539
    Prev
    Next
    INDEX
    Explanations

    instances of the word "break" or its variations, indicating actions of separation or disruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mouseY
    -0.55
     McIntosh
    -0.48
     zeros
    -0.47
    Gruß
    -0.47
    inerja
    -0.46
     quantità
    -0.45
    AccessType
    -0.45
    umán
    -0.45
    Datum
    -0.45
     Lordships
    -0.44
    POSITIVE LOGITS
     breaking
    1.50
     break
    1.44
     breaks
    1.39
     Break
    1.38
     BREAK
    1.38
    break
    1.37
     Breaks
    1.37
     Breaking
    1.36
    Break
    1.35
    Breaking
    1.35
    Activations Density 0.111%

    No Known Activations