© 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. 33-GEMMASCOPE-RES-16K
    11. 7308
    Prev
    Next
    INDEX
    Explanations

    references to fatal injuries and their consequences in legal or medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rine
    -0.35
    實在
    -0.33
    consulté
    -0.33
     پس
    -0.32
    时候
    -0.32
    нцип
    -0.32
    brä
    -0.31
    OrBuilder
    -0.31
    Cyfarwyddwr
    -0.30
     Enum
    -0.30
    POSITIVE LOGITS
     consequence
    2.20
     result
    2.19
     conséquence
    1.82
     consecuencia
    1.81
     conseguenza
    1.78
    Consequently
    1.77
    result
    1.77
     Result
    1.76
     Consequently
    1.75
     consequently
    1.70
    Activations Density 0.660%

    No Known Activations