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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 103163
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as classes and templates in programming languages

    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
    ตรี
    -0.37
    SceneManagement
    -0.32
     صاد
    -0.32
     once
    -0.31
    ēj
    -0.31
    utados
    -0.31
     яких
    -0.30
    DateUtils
    -0.30
    iness
    -0.30
     anxiety
    -0.30
    POSITIVE LOGITS
     CreateTagHelper
    0.73
    RectangleBorder
    0.73
    expandindo
    0.73
    __(/*!
    0.72
    ftagPool
    0.71
     pinulongan
    0.70
    تقاوى
    0.69
    帖最后由
    0.69
    parsedMessage
    0.68
    adaptiveStyles
    0.67
    Activations Density 0.026%

    No Known Activations