© 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. 10-GEMMASCOPE-RES-16K
    11. 6132
    Prev
    Next
    INDEX
    Explanations

    names and references related to legal cases and individuals involved in the justice system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gentry
    -0.51
     McCormack
    -0.48
     Hennessy
    -0.48
    OMET
    -0.46
    animales
    -0.46
    Memphis
    -0.45
     errorMsg
    -0.44
    college
    -0.44
    joven
    -0.44
    contenedor
    -0.44
    POSITIVE LOGITS
    UserScript
    0.63
    Slf
    0.63
     Administrativna
    0.57
    SBATCH
    0.57
    Tē
    0.55
     createState
    0.52
    — 
    0.51
    tagHelper
    0.50
     iParam
    0.49
    (--
    0.48
    Activations Density 2.047%

    No Known Activations