© 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. 25-GEMMASCOPE-RES-16K
    6. 744
    Prev
    Next
    INDEX
    Explanations

    documents that reference regulatory and administrative processes, particularly in relation to heritage and citizenship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __*/
    -0.52
    躇
    -0.50
    droje
    -0.49
    Šaltiniai
    -0.49
     nakalista
    -0.48
    ADELPHIA
    -0.47
    WithIOException
    -0.47
     luận
    -0.47
    ektiv
    -0.47
    Hauptartikel
    -0.46
    POSITIVE LOGITS
     Ministry
    0.92
     competent
    0.82
     Directorate
    0.80
     ministry
    0.80
    Ministry
    0.78
     ministries
    0.70
     MINISTRY
    0.68
    competent
    0.67
     authority
    0.67
    queryInterface
    0.66
    Activations Density 0.318%

    No Known Activations