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. 8111
    Prev
    Next
    INDEX
    Explanations

    key information in a narrative, particularly regarding events, timelines, and relationships among subjects involved

    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
    Predecesor
    -0.56
    OGND
    -0.55
    DockStyle
    -0.53
     OMITBAD
    -0.48
    发表于
    -0.48
     resourceCulture
    -0.48
    كويكب
    -0.48
    ,:),
    -0.47
    boom
    -0.46
    TRAILING
    -0.45
    POSITIVE LOGITS
    Rüyada
    0.40
    enterOuterAlt
    0.38
    日閲覧
    0.35
    modelBuilder
    0.34
    一来
    0.34
     favoritas
    0.33
     délais
    0.33
    ंदीखरीदारी
    0.32
    Manbalar
    0.31
     Anerkennung
    0.31
    Activations Density 0.237%

    No Known Activations