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. 12-GEMMASCOPE-RES-16K__L0-22
    6. 75
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Życiorys
    -0.55
     BLANK
    -0.46
     Pho
    -0.45
     Datenschutzer
    -0.45
    GEBURTSDATUM
    -0.44
    CPtr
    -0.44
    leiding
    -0.43
     Gins
    -0.43
    ско
    -0.42
     Kelle
    -0.42
    POSITIVE LOGITS
     الحره
    0.75
     متعلقه
    0.75
    TagMode
    0.68
    bootstrapcdn
    0.67
    __':
    
    0.66
     GenerationType
    0.66
     BoxFit
    0.64
    دانشنامهٔ
    0.64
     AssemblyCulture
    0.63
     **/
    
    0.60
    Activations Density 0.042%

    No Known Activations