Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 6073
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references related to court proceedings and judicial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setAddress
    -0.59
    ěst
    -0.53
     Rady
    -0.53
    例句
    -0.53
     statewide
    -0.51
    Xna
    -0.50
    favourable
    -0.50
     Legislature
    -0.49
     Coupons
    -0.49
     gyhoeddwyd
    -0.49
    POSITIVE LOGITS
     Federal
    0.85
     federal
    0.81
    Federal
    0.80
     Congressional
    0.69
     FEDERAL
    0.67
     Congress
    0.66
    bewerken
    0.64
     كومونز
    0.64
    federal
    0.62
    ressional
    0.61
    Activations Density 1.382%

    No Known Activations