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. 20-GEMMASCOPE-RES-16K
    6. 5471
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and procedural aspects of law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows citations (case law)

    np_acts-logits-general · gemini-2.0-flash

    legal citation punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    __*/
    -0.57
     Ressource
    -0.55
    WritableDatabase
    -0.53
     Dostupné
    -0.52
    LikeLike
    -0.51
    szak
    -0.51
    protoimpl
    -0.49
     scattata
    -0.48
    DataSetChanged
    -0.47
    stdc
    -0.46
    POSITIVE LOGITS
    fromnode
    0.61
    httphttps
    0.57
    OGND
    0.57
     sumpay
    0.56
    RegistryLite
    0.55
    ナソニック
    0.55
    теризу
    0.51
    філь
    0.51
    isiaj
    0.50
    Personensuche
    0.50
    Activations Density 1.743%

    No Known Activations