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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-GEMMASCOPE-RES-16K
    6. 6976
    Prev
    Next
    INDEX
    Explanations

    opening and closing parentheses and braces in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chun
    -0.65
    INTERFACE
    -0.61
     Sauce
    -0.59
    antía
    -0.59
    tangentMode
    -0.57
     looks
    -0.57
    yip
    -0.55
    uarga
    -0.54
    pony
    -0.54
    alchemy
    -0.53
    POSITIVE LOGITS
    '){
    3.50
    "){
    3.49
    ']){
    3.19
    '){
    
    3.16
    ')){
    3.15
    ")){
    3.06
    "){
    
    3.05
    )){
    3.03
    ]){
    3.02
    '])){
    2.99
    Activations Density 0.129%

    No Known Activations