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. 23122
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing assistance or 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
     surla
    -0.63
    
    -0.53
     esternos
    -0.53
     estekak
    -0.46
     referenties
    -0.44
    Portály
    -0.43
    Tembelea
    -0.42
     yoksa
    -0.42
    vejec
    -0.42
     فريبيس
    -0.42
    POSITIVE LOGITS
    ViewFeatures
    0.50
    ontent
    0.44
     Lem
    0.44
     tuyến
    0.43
     readers
    0.43
    posedge
    0.42
    displaymath
    0.42
     Schwert
    0.41
    Lem
    0.40
    xyl
    0.40
    Activations Density 0.057%

    No Known Activations