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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12938
    Prev
    Next
    INDEX
    Explanations

    elements related to formatting and references in academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Gön
    -0.56
    cèse
    -0.52
    Hozzáférés
    -0.49
     ligiloj
    -0.48
    webElementGuid
    -0.48
    ագրություններ
    -0.47
     rechange
    -0.47
    
    -0.46
     disambiguazione
    -0.46
    ⓧ
    -0.46
    POSITIVE LOGITS
    锈钢
    0.42
    csolódó
    0.40
     Administrativna
    0.40
    Personendaten
    0.38
    ACHUSET
    0.37
    adro
    0.36
    windowFixed
    0.36
    (;;)
    0.35
     Numerade
    0.35
    kháu
    0.34
    Activations Density 0.567%

    No Known Activations