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. 9-GEMMASCOPE-RES-16K
    6. 3396
    Prev
    Next
    INDEX
    Explanations

    method calls and their parameters related to retrieving or searching for objects in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.32
     مشارکت‌کنندگان
    -0.31
     itſelf
    -0.31
    RepeatedField
    -0.28
    Ground
    -0.28
    theless
    -0.27
    ยว
    -0.27
     ground
    -0.26
     Almería
    -0.26
     AssemblyProduct
    -0.26
    POSITIVE LOGITS
    findById
    1.18
     findById
    1.09
    ById
    0.98
    findBy
    0.93
     findBy
    0.92
    ByUsername
    0.87
     getById
    0.87
    ByName
    0.87
     deleteById
    0.85
    getById
    0.85
    Activations Density 0.237%

    No Known Activations