© 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-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 7019
    Prev
    Next
    INDEX
    Explanations

    expressions related to legal and judicial terms

    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
     HasFactory
    -0.82
     AssemblyCompany
    -0.80
    Hentet
    -0.74
     surla
    -0.73
    featureID
    -0.71
    SBATCH
    -0.71
    SharedDtor
    -0.69
     picioare
    -0.69
    MethodManager
    -0.69
     Chwiliwch
    -0.69
    POSITIVE LOGITS
    Pres
    0.39
     Pres
    0.38
     съ
    0.35
     tình
    0.32
     Rah
    0.31
     alla
    0.31
     qual
    0.31
     Sus
    0.31
     Gr
    0.31
     sob
    0.30
    Activations Density 0.825%

    No Known Activations