© 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. 10-GEMMASCOPE-RES-16K
    11. 16017
    Prev
    Next
    INDEX
    Explanations

    text related to legal proceedings and the roles of attorneys in those contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
    <bos>
    -0.69
    Portály
    -0.65
     Werth
    -0.60
    GEBURTSDATUM
    -0.59
    swt
    -0.56
    Zitat
    -0.55
     Caribe
    -0.54
     Mechanical
    -0.53
    KEYCODE
    -0.52
    insch
    -0.52
    POSITIVE LOGITS
    Prosecutors
    1.07
     prosecutors
    1.06
     Prosecutor
    1.04
     prosecutor
    1.03
     prosecuting
    0.92
     prosecution
    0.90
     Prosec
    0.88
     prosec
    0.86
    Prosec
    0.85
     prosecute
    0.84
    Activations Density 0.453%

    No Known Activations