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. 6-GEMMASCOPE-RES-16K
    6. 12187
    Prev
    Next
    INDEX
    Explanations

    instances of the "beginning of sentence" or narrative transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnimationsModule
    -0.83
     defaultstate
    -0.78
     للمعارف
    -0.68
     BoxFit
    -0.63
     AssemblyCompany
    -0.63
     tslint
    -0.62
    TintMode
    -0.62
     clearColor
    -0.61
    colorbar
    -0.61
    órc
    -0.61
    POSITIVE LOGITS
    __':
    
    1.05
     الحره
    0.89
    __":
    
    0.85
    __':
    0.82
    InvalidProtocol
    0.78
    ↵↵
    0.77
    __":
    0.75
    []){
    0.74
    RegressionTest
    0.71
    <bos>
    0.70
    Activations Density 0.072%

    No Known Activations