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. 7-GEMMASCOPE-RES-16K
    6. 6333
    Prev
    Next
    INDEX
    Explanations

    instances of the auxiliary verb "have" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lester
    -0.90
    
    -0.89
    ГЛА
    -0.87
     Whistle
    -0.86
    Datuak
    -0.82
    IUrlHelper
    -0.80
     Wiktionnaire
    -0.80
    parsedMessage
    -0.78
    Lester
    -0.76
    lamabad
    -0.76
    POSITIVE LOGITS
     Ive
    1.21
     been
    1.21
    ve
    1.17
    Ive
    1.11
     ive
    0.97
    Been
    0.91
    )),
    
    0.87
     Been
    0.84
     gotta
    0.83
    been
    0.82
    Activations Density 0.032%

    No Known Activations