© 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. 14742
    Prev
    Next
    INDEX
    Explanations

    terms related to escape and enterprise contexts

    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
    Enumerator
    -0.54
    prest
    -0.54
     cheveux
    -0.52
    prav
    -0.51
    conia
    -0.49
     Iglesias
    -0.49
     gius
    -0.49
     Zwick
    -0.48
     الص
    -0.47
     trå
    -0.47
    POSITIVE LOGITS
     escape
    0.89
     escaping
    0.88
     Campbell
    0.80
     Escape
    0.77
     ModelExpression
    0.76
     ESCAPE
    0.74
     escaped
    0.73
    Према
    0.71
     escapes
    0.70
    parsedMessage
    0.69
    Activations Density 0.095%

    No Known Activations