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. 122986
    Prev
    Next
    INDEX
    Explanations

    email communication structure, particularly recipient and sender formatting

    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
    ngrx
    -0.51
    ształ
    -0.49
     Commencez
    -0.49
    initializeApp
    -0.49
    badlogic
    -0.49
    Références
    -0.48
    arschu
    -0.47
     فريبيس
    -0.47
    quelize
    -0.47
    ècie
    -0.47
    POSITIVE LOGITS
    Datuak
    0.39
    sidemargin
    0.39
    outWeight
    0.39
     ErrIntOverflow
    0.37
     ***!
    0.37
    ViewFeatures
    0.36
    DebuggerNonUser
    0.35
    jspx
    0.34
    OrBuilder
    0.34
    ọi
    0.33
    Activations Density 0.020%

    No Known Activations