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. 3-GEMMASCOPE-RES-16K
    6. 12736
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to judgments and convictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EnableWeb
    -0.75
    remadura
    -0.69
    hdessä
    -0.66
    ειτουργ
    -0.64
     edifice
    -0.62
     Gegenteil
    -0.61
    yaitu
    -0.60
    περ
    -0.60
     crate
    -0.60
    wanza
    -0.58
    POSITIVE LOGITS
     judgment
    3.02
     judgement
    2.77
     Judgment
    2.69
    judgment
    2.56
    Judgment
    2.51
     Judgement
    2.46
     judgments
    2.45
     JUDGMENT
    2.39
     judgements
    2.26
     jugement
    1.86
    Activations Density 0.133%

    No Known Activations