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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9671
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to petitions and claims in a judicial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dirait
    -0.49
     jati
    -0.49
    BoxLayout
    -0.48
     faſt
    -0.46
    altezza
    -0.46
     jalur
    -0.46
    licator
    -0.46
    žius
    -0.45
     voli
    -0.45
     deſt
    -0.44
    POSITIVE LOGITS
    contentLoaded
    0.80
    Datuak
    0.73
    LookAnd
    0.72
    RectangleBorder
    0.66
     متعلقه
    0.65
    IndentedString
    0.65
     ddelweddau
    0.64
     незавершена
    0.63
    MigrationBuilder
    0.61
    RTEX
    0.61
    Activations Density 0.262%

    No Known Activations