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. 23-GEMMASCOPE-RES-131K
    6. 54
    Prev
    Next
    INDEX
    Explanations

    statements related to customer engagement and support

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.72
     يتيمه
    -0.64
     disponibilités
    -0.59
     propOrder
    -0.57
    
    -0.55
     autorytatywna
    -0.54
     InputDecoration
    -0.54
    Tracce
    -0.53
    期刊论文
    -0.52
     wikipagina
    -0.51
    POSITIVE LOGITS
     welcomes
    0.35
    hira
    0.35
     welcome
    0.34
    Herzlich
    0.32
     hope
    0.32
    ​
    0.31
    Welcome
    0.31
    よろしくお願いします
    0.31
    本质
    0.30
    <eos>
    0.30
    Activations Density 0.015%

    No Known Activations