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. 6138
    Prev
    Next
    INDEX
    Explanations

    patterns associated with loop constructs and control flow in programming code

    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
    ########.
    -0.64
     good
    -0.60
    itinéraire
    -0.53
    werke
    -0.52
     better
    -0.50
     թվական
    -0.49
     peine
    -0.49
    TRIBUN
    -0.47
    Portale
    -0.47
     Planet
    -0.46
    POSITIVE LOGITS
    __':
    
    0.84
    modelBuilder
    0.78
    ++){
    
    0.77
    ViewImports
    0.76
     الحره
    0.72
     HasFactory
    0.69
     MonoBehaviour
    0.69
    __":
    
    0.68
    --){
    0.67
    __':
    0.66
    Activations Density 0.029%

    No Known Activations