Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 6257
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Fu" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    meability
    -0.61
    mybatisplus
    -0.57
     Renaud
    -0.55
    writerow
    -0.55
     pard
    -0.53
     umbre
    -0.53
    Compiled
    -0.53
    xmlns
    -0.53
     Dawkins
    -0.53
    ladel
    -0.51
    POSITIVE LOGITS
     fu
    0.85
     feared
    0.79
     deer
    0.69
     Fu
    0.69
     fears
    0.67
    Fu
    0.67
    reportWebVitals
    0.66
    ond
    0.66
    Portale
    0.65
     fear
    0.62
    Activations Density 0.102%

    No Known Activations