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. 90
    Prev
    Next
    INDEX
    Explanations

    terms related to avoidance or evasion of actions or concepts

    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
     publiques
    -0.73
     extérieures
    -0.71
     vertes
    -0.70
     privées
    -0.67
     Sutherland
    -0.66
     Catt
    -0.66
    chromedriver
    -0.64
    mesg
    -0.64
    睦
    -0.63
    JMenu
    -0.63
    POSITIVE LOGITS
    avoid
    1.82
     Avoid
    1.80
    Avoid
    1.78
     avoid
    1.73
     AVOID
    1.68
     avoided
    1.65
     avoiding
    1.64
     Avoidance
    1.55
     avoids
    1.55
     avoidance
    1.55
    Activations Density 0.061%

    No Known Activations