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. 24-GEMMASCOPE-RES-131K
    6. 775
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    school. , power company , orchestra , http , orchestra , unified parents , smcs. , circuit , http , 8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.75
     betweenstory
    -0.67
    ViewImports
    -0.67
    
    -0.66
    <unused16>
    -0.65
    rungsseite
    -0.65
    fjspx
    -0.65
    <unused79>
    -0.65
    <unused23>
    -0.65
    <unused3>
    -0.65
    POSITIVE LOGITS
    bukaan
    0.27
     görül
    0.26
     olmaz
    0.23
     malade
    0.23
    vierung
    0.23
     comprendre
    0.23
     actualizaciones
    0.22
     Numerade
    0.22
     attuale
    0.21
     Então
    0.20
    Activations Density 0.117%

    No Known Activations