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. 122837
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific disciplines and academic journals

    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
     surla
    -0.61
    RuleContext
    -0.48
    出版年
    -0.46
    IsContent
    -0.46
     ſch
    -0.45
    Бележки
    -0.43
    XtraBars
    -0.43
     habet
    -0.43
     كومونز
    -0.43
     argint
    -0.40
    POSITIVE LOGITS
     estekak
    0.57
    AndroidJUnit
    0.46
    InputBorder
    0.42
    JvmStatic
    0.42
    ⓧ
    0.41
    Carriera
    0.37
    PYX
    0.36
    joba
    0.36
     مرئيه
    0.36
    คง
    0.36
    Activations Density 0.010%

    No Known Activations