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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 5661
    Prev
    Next
    INDEX
    Explanations

    elements related to legal terminology and processes, particularly surrounding consent and representative roles in court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EClass
    -0.53
    PageIndex
    -0.47
    Joining
    -0.47
    knex
    -0.46
     ***!
    -0.45
    stdc
    -0.43
     rek
    -0.42
    tock
    -0.40
     Angebot
    -0.40
    erir
    -0.40
    POSITIVE LOGITS
    atorship
    0.80
    DeleteBehavior
    0.72
     kasarigan
    0.72
     <=",
    0.71
     guardianship
    0.68
    Спољашње
    0.67
    بوابة
    0.67
    Kjelder
    0.67
     ObjectParameter
    0.67
    bootstrapcdn
    0.66
    Activations Density 0.524%

    No Known Activations