© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 13873
    Prev
    Next
    INDEX
    Explanations

    concepts related to evaluation and judgment in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    readystatechange
    -0.52
    TryParse
    -0.50
    риди
    -0.50
    wsgi
    -0.49
     tun
    -0.48
    ModelState
    -0.48
    umb
    -0.47
     pie
    -0.47
     President
    -0.46
    ark
    -0.46
    POSITIVE LOGITS
     пользователем
    0.60
     saites
    0.56
     hâte
    0.56
     BorderSide
    0.55
     pinulongan
    0.54
     ſeveral
    0.54
    tagHelperRunner
    0.54
     oleh
    0.54
     вікі
    0.54
     semula
    0.54
    Activations Density 1.686%

    No Known Activations