© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8683
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "argument" as well as related discussions and claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    rrggbb
    -0.56
     OSI
    -0.56
     Whitby
    -0.54
    issauga
    -0.53
     Dina
    -0.52
    :");
    
    -0.51
     مرئيه
    -0.50
    )<\
    -0.50
    )");
    
    -0.50
     esternos
    -0.49
    POSITIVE LOGITS
     argument
    1.35
     arguments
    1.28
     argue
    1.24
    argument
    1.24
     Argument
    1.22
    Argument
    1.21
     argued
    1.21
     Arguments
    1.15
    arguments
    1.15
     arguing
    1.12
    Activations Density 0.140%

    No Known Activations