© 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. 22-GEMMASCOPE-RES-16K
    11. 6782
    Prev
    Next
    INDEX
    Explanations

    the structure and components of objects, particularly when describing their dimensions and positions

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

    Position within a physical object

    np_acts-logits-general · gemini-2.0-flash

    locations and parts

    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
     Normdatei
    -0.77
     ujednoznacz
    -0.75
     InputDecoration
    -0.68
    ModelSerializer
    -0.66
    addCriterion
    -0.65
     الرياضيه
    -0.65
     @"/
    -0.63
     AssemblyCulture
    -0.62
    makeConstraints
    -0.62
    évaluateur
    -0.62
    POSITIVE LOGITS
     portion
    1.45
     part
    1.27
     section
    1.13
    most
    1.12
     portions
    1.03
    portion
    1.02
     half
    0.96
    MOST
    0.89
     parts
    0.88
    部分
    0.87
    Activations Density 0.494%

    No Known Activations