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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 3571
    Prev
    Next
    INDEX
    Explanations

    terms related to bypassing and navigating around obstacles or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lardır
    -0.48
     mancha
    -0.39
    ื
    -0.37
    ActionCreators
    -0.36
    inplace
    -0.35
     shew
    -0.35
     oxígeno
    -0.35
     action
    -0.34
    har
    -0.34
     mater
    -0.34
    POSITIVE LOGITS
    CopyWith
    0.94
    tagHelperRunner
    0.93
     ModelExpression
    0.90
    بوابة
    0.87
     bypassing
    0.87
     melewati
    0.85
     AssemblyCompany
    0.85
     overcame
    0.84
    SourceChecksum
    0.83
     overcoming
    0.82
    Activations Density 0.240%

    No Known Activations