Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 29704
    Prev
    Next
    INDEX
    Explanations

    terms related to programming concepts and structures

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     незавершена
    -0.48
    DockStyle
    -0.47
    XmlAccessorType
    -0.45
    Geplaatst
    -0.43
    ьаж
    -0.42
     Administrativna
    -0.40
    دانشنامهٔ
    -0.40
     BioLib
    -0.39
    EDEFAULT
    -0.39
    astéroïdes
    -0.37
    POSITIVE LOGITS
    Personendaten
    0.56
    들의
    0.56
     ddelweddau
    0.54
     statuses
    0.49
     الوا
    0.46
    wegen
    0.46
     fittest
    0.45
     wards
    0.45
     ده
    0.44
     groups
    0.43
    Activations Density 0.043%

    No Known Activations