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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 36546
    Prev
    Next
    INDEX
    Explanations

    programming constructs and code structure elements relevant to object-oriented programming

    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
    ScopeManager
    -0.50
    celotti
    -0.42
     mxArray
    -0.40
    ArrowToggle
    -0.40
    ⓧ
    -0.38
    XmlAccessorType
    -0.38
     uska
    -0.37
    ốc
    -0.37
     @"/
    -0.37
    atguigu
    -0.36
    POSITIVE LOGITS
    lapsingToolbar
    0.44
    balleur
    0.43
    ensement
    0.41
    #+#
    0.40
    Décès
    0.40
     Sambo
    0.39
     traves
    0.39
    Gweler
    0.39
     виправивши
    0.38
    crí
    0.38
    Activations Density 0.064%

    No Known Activations