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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24-GEMMASCOPE-RES-16K
    6. 14061
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and heritage

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

    Italian language punctuation

    np_acts-logits-general · gemini-2.0-flash

    Italian location names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WEBPACK
    -0.54
     enough
    -0.52
    irage
    -0.48
     secondary
    -0.47
     closed
    -0.47
     advantage
    -0.47
     were
    -0.47
     kinds
    -0.47
     everything
    -0.46
     primarily
    -0.46
    POSITIVE LOGITS
     varandra
    0.61
     vägen
    0.54
     larmes
    0.54
     stället
    0.53
     colère
    0.51
     brancas
    0.51
     lettura
    0.50
     poussière
    0.50
     sempre
    0.49
     bénévoles
    0.49
    Activations Density 0.104%

    No Known Activations