© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2568
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to court proceedings and rulings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stateMutability
    -0.67
    arre
    -0.58
    Datuak
    -0.56
     Goddard
    -0.54
    tidase
    -0.53
     wpis
    -0.51
     petition
    -0.51
    lgari
    -0.50
     coordinates
    -0.49
    apatilla
    -0.49
    POSITIVE LOGITS
     jury
    1.25
     jurors
    1.06
     juries
    1.00
     Jury
    0.97
    jury
    0.95
    Jury
    0.94
    Jur
    0.87
     juror
    0.85
     jurado
    0.81
     verdict
    0.79
    Activations Density 1.601%

    No Known Activations