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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 3571
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and parameters, particularly those related to ports, variables, and image formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (){
    
    -0.54
    ()){
    
    -0.50
     DbSet
    -0.46
    ();
    
    
    -0.44
     rival
    -0.44
    !")
    
    -0.43
    funeralhome
    -0.41
    '){
    
    -0.41
    (){
    -0.40
    WebElementEntity
    -0.40
    POSITIVE LOGITS
     مرئيه
    0.75
     ->
    0.73
     으로
    0.71
     =>
    0.69
     дописавши
    0.67
     instead
    0.65
     or
    0.65
     <--
    0.63
     esetén
    0.63
     assuming
    0.63
    Activations Density 2.294%

    No Known Activations