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. 22-GEMMASCOPE-RES-16K
    6. 5857
    Prev
    Next
    INDEX
    Explanations

    terms related to legal processes, especially concerning jury management and administration

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

    ending in "tration," "rations," "ral," "ries," "rate," "ric," or "red"

    np_acts-logits-general · gemini-2.0-flash

    administration, registration, arbitration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     smer
    -0.43
    Personendaten
    -0.43
    ations
    -0.43
    olisme
    -0.42
     متعلقه
    -0.42
     Beller
    -0.42
     tappa
    -0.41
    ation
    -0.40
    ایی
    -0.39
     automatiques
    -0.39
    POSITIVE LOGITS
    rate
    0.69
    tral
    0.68
    trat
    0.67
    trate
    0.66
    rated
    0.65
    tr
    0.63
    trin
    0.63
    rates
    0.62
    rítica
    0.62
    brates
    0.60
    Activations Density 0.419%

    No Known Activations