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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 1757
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to properties of objects, particularly in geometry and topology

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

    Mathematical properties/conditions

    np_acts-logits-general · gemini-2.0-flash

    mathematical existence and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '){
    
    -0.55
    Intersect
    -0.53
    ”-
    -0.52
    収録曲
    -0.52
    риа
    -0.52
    ulco
    -0.51
    =$?
    -0.51
    […]
    -0.51
    figsize
    -0.50
    ++){
    
    -0.50
    POSITIVE LOGITS
     feroit
    0.78
     aveug
    0.78
     ovunque
    0.78
     religieuses
    0.76
     everywhere
    0.75
     auroit
    0.75
     térmico
    0.70
    XmlAccessType
    0.68
     étoient
    0.68
     mourut
    0.68
    Activations Density 1.772%

    No Known Activations