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

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 6209
    Prev
    Next
    INDEX
    Explanations

    references to imprisonment, sentencing, and legal penalties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Erstellt
    -0.43
     defaultstate
    -0.41
    šn
    -0.37
    cplusplus
    -0.37
    ighed
    -0.35
    orté
    -0.35
     незавершена
    -0.35
    出版年
    -0.35
     vyb
    -0.35
     equilibr
    -0.34
    POSITIVE LOGITS
     prison
    2.39
     jail
    2.36
     imprisonment
    2.05
    prison
    2.03
     Prison
    2.03
     prisons
    2.00
    Prison
    1.97
     imprisoned
    1.95
     Jail
    1.92
     PRISON
    1.87
    Activations Density 0.580%

    No Known Activations