© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 16035
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court cases and judicial decisions

    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
     виправивши
    -0.43
    PARATUS
    -0.42
    PropertyChanging
    -0.41
     mostaza
    -0.40
    sonaro
    -0.40
     iprot
    -0.39
    Notae
    -0.38
     esmalte
    -0.38
    туга
    -0.38
    ActionMode
    -0.36
    POSITIVE LOGITS
     case
    0.63
     cases
    0.60
    cases
    0.53
     Case
    0.52
    case
    0.52
    Case
    0.51
     pending
    0.51
    trial
    0.50
     Cases
    0.48
    ISupport
    0.48
    Activations Density 1.729%

    No Known Activations