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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8464
    Prev
    Next
    INDEX
    Explanations

    mentions of personal activities or interactions, particularly those involving technology and social engagement

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     ujednoznacz
    -0.44
    getDoctrine
    -0.44
    municipi
    -0.35
    getResultList
    -0.34
    JAKARTA
    -0.34
     strop
    -0.32
    intellij
    -0.32
     inget
    -0.32
    inek
    -0.31
    ecore
    -0.31
    POSITIVE LOGITS
    OGND
    0.59
     cherchés
    0.58
    цезда
    0.52
    MigrationBuilder
    0.51
    новниш
    0.50
    (!__
    0.49
    ViewFeatures
    0.48
    BufferException
    0.45
    outSlope
    0.44
    лтемелер
    0.44
    Activations Density 0.508%

    No Known Activations