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. 117358
    Prev
    Next
    INDEX
    Explanations

    items and actions related to processing or preparing materials, particularly in a scientific or experimental context

    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
     초
    -0.42
    astanza
    -0.41
     propri
    -0.41
    UrlResolution
    -0.41
    Zitat
    -0.40
    Vaata
    -0.40
    inhas
    -0.39
     Hol
    -0.39
    getMock
    -0.37
     engagement
    -0.37
    POSITIVE LOGITS
    تقاوى
    0.48
     BrowserModule
    0.45
    HideFlags
    0.45
    ImageContext
    0.44
     BoxFit
    0.43
    RTHOOK
    0.43
     Administrativna
    0.39
    +#+#
    0.39
     SafeMath
    0.39
    classmethod
    0.38
    Activations Density 0.043%

    No Known Activations