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. 2-GEMMASCOPE-RES-16K
    6. 3809
    Prev
    Next
    INDEX
    Explanations

    repeated references to "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.97
     AssemblyCulture
    -0.79
     سكانية
    -0.76
    ValueStyle
    -0.71
    ]);
    
    -0.70
    oa̍t
    -0.67
    DropColumn
    -0.65
    ="">
    
    -0.65
    ]));
    
    -0.65
    MessageTagHelper
    -0.64
    POSITIVE LOGITS
     Wikimedijinoj
    0.53
    таратура
    0.50
    NSYLVANIA
    0.50
     Coronation
    0.48
    apimachinery
    0.47
    unix
    0.47
    rizona
    0.46
     tă
    0.44
     coronation
    0.44
    sstream
    0.44
    Activations Density 0.629%

    No Known Activations