© 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. 11-GEMMASCOPE-RES-16K
    11. 10292
    Prev
    Next
    INDEX
    Explanations

    references to injury, damages, and liability in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     libremente
    -0.47
     constantemente
    -0.47
     mukana
    -0.46
     nessuno
    -0.45
     ancianos
    -0.43
    yeb
    -0.43
     Czer
    -0.43
    OGND
    -0.42
    ließlich
    -0.42
     synonymous
    -0.41
    POSITIVE LOGITS
     damage
    1.70
     Damage
    1.59
    damage
    1.55
    Damage
    1.48
     DAMAGE
    1.39
     damages
    1.29
     Damages
    1.26
    DAMAGE
    1.20
     damaged
    1.13
     daño
    1.11
    Activations Density 0.206%

    No Known Activations