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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 102978
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes related to data structures and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.85
    ⤹
    -0.84
    bootstrapcdn
    -0.80
    Autoritní
    -0.80
    Personendaten
    -0.79
    GEBURTSDATUM
    -0.78
    
    -0.76
    uxxxx
    -0.75
    出版年
    -0.71
    findpost
    -0.71
    POSITIVE LOGITS
    .
    0.39
     sk
    0.35
     llegar
    0.33
     llegará
    0.32
    1
    0.32
     llegue
    0.31
     Harg
    0.31
     seems
    0.30
    .)
    0.30
    दो
    0.30
    Activations Density 0.016%

    No Known Activations