© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 5824
    Prev
    Next
    INDEX
    Explanations

    words related to escaping or avoidance from difficult situations

    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
    ём
    -0.52
    er
    -0.50
    wsj
    -0.48
     hã
    -0.48
     ECR
    -0.47
    ms
    -0.47
    mo
    -0.47
     stoi
    -0.47
     dinners
    -0.47
    ൂ
    -0.47
    POSITIVE LOGITS
     escape
    0.96
     escaped
    0.96
     escapes
    0.91
     Escape
    0.87
     unt
    0.83
    escaping
    0.81
     escaping
    0.81
    attributes
    0.80
    granate
    0.80
     trained
    0.77
    Activations Density 0.083%

    No Known Activations