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. 14-GEMMASCOPE-RES-16K
    6. 4113
    Prev
    Next
    INDEX
    Explanations

    conjunctions and variations of the word "or."

    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
    )");
    
    -0.97
     BMS
    -0.88
    $")
    -0.84
     ―――――
    -0.83
    %");
    -0.82
     fevere
    -0.81
     Cuenca
    -0.81
     Manta
    -0.79
     Aquila
    -0.79
     Festa
    -0.79
    POSITIVE LOGITS
     Or
    1.23
     OR
    1.07
    Or
    1.06
     Ortiz
    0.98
    or
    0.96
     or
    0.95
    OR
    0.92
     eller
    0.90
     else
    0.89
     otherwise
    0.87
    Activations Density 0.150%

    No Known Activations