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. 1-GEMMASCOPE-RES-16K
    6. 13598
    Prev
    Next
    INDEX
    Explanations

    patterns in data structures, specifically focusing on array and list notations

    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
    StoryboardSegue
    -1.13
     незавершена
    -1.04
     itſelf
    -0.99
     ―――――
    -0.97
    oredCriteria
    -0.97
    IsInitialized
    -0.96
    contentLoaded
    -0.92
    RTEE
    -0.90
    Geplaatst
    -0.90
     betweenstory
    -0.89
    POSITIVE LOGITS
     [
    1.39
    =[
    1.05
    ([
    1.02
    ={[
    0.89
     =[
    0.82
    :[
    0.81
     [[
    0.79
    }=[
    0.79
     [
    
    0.79
    :[
    0.79
    Activations Density 0.542%

    No Known Activations