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. 23-GEMMASCOPE-RES-16K
    6. 11307
    Prev
    Next
    INDEX
    Explanations

    instances of code utilization, particularly in programming contexts involving implementation and logic handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     témoignages
    -0.65
     actuelles
    -0.64
     actuels
    -0.59
     démocr
    -0.59
     âgées
    -0.57
     atuais
    -0.56
     prisonniers
    -0.56
     ninguém
    -0.56
     navires
    -0.55
     brancas
    -0.53
    POSITIVE LOGITS
     logic
    0.92
     actions
    0.91
     operations
    0.91
     functionality
    0.80
     stuff
    0.78
     commands
    0.77
     handling
    0.75
     functions
    0.75
     manipulations
    0.74
     interactions
    0.71
    Activations Density 1.048%

    No Known Activations