© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2730
    Prev
    Next
    INDEX
    Explanations

    elements related to anatomical and physiological abnormalities, particularly in the context of developmental changes and cellular structures

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

    Cell or material structure/organization

    np_acts-logits-general · gemini-2.0-flash

    structure and spatial organization

    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
    JspWriter
    -0.79
    tagHelperRunner
    -0.74
     ligiloj
    -0.65
    FontOfSize
    -0.59
    BeginContext
    -0.59
     tartalomajánló
    -0.57
     otomatig
    -0.57
     démocratie
    -0.56
    MultipartFile
    -0.56
    期刊论文
    -0.56
    POSITIVE LOGITS
     structure
    2.00
    structure
    1.65
     Structure
    1.48
    Structure
    1.43
     architecture
    1.42
     morphology
    1.41
     topology
    1.40
     STRUCTURE
    1.37
     configuration
    1.36
     structures
    1.31
    Activations Density 1.520%

    No Known Activations