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. 12764
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating connections or relationships between ideas

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

    Preceding "and" followed by function/motion/stigma

    np_acts-logits-general · gemini-2.0-flash

    cause and effect relationship

    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
     ingenieros
    -0.72
     and
    -0.63
    :
    -0.59
     hizo
    -0.57
     intentó
    -0.56
     infecciones
    -0.56
     ilustraciones
    -0.56
     emozioni
    -0.55
     både
    -0.55
    ResumeLayout
    -0.55
    POSITIVE LOGITS
     hence
    1.72
     therefore
    1.62
     thus
    1.56
     consequently
    1.41
    rogens
    1.41
    hence
    1.36
     other
    1.36
     thereby
    1.36
     dermed
    1.33
    /
    1.30
    Activations Density 1.451%

    No Known Activations