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. 23163
    Prev
    Next
    INDEX
    Explanations

    locations and educational institutions

    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
     MainAxisSize
    -0.55
    writeFieldEnd
    -0.54
    MemoryWarning
    -0.51
     فريبيس
    -0.51
     चीज़ों
    -0.51
    zzleHttp
    -0.50
    twimg
    -0.49
    новниш
    -0.48
    mistry
    -0.47
    webElementXpaths
    -0.47
    POSITIVE LOGITS
    ReusableCell
    0.42
    Cyfeiriadau
    0.38
    الدراسه
    0.38
    BorderFactory
    0.37
    SourceChecksum
    0.37
    ütfen
    0.33
     serve
    0.33
     gjelder
    0.32
     äta
    0.32
    fillType
    0.32
    Activations Density 0.001%

    No Known Activations