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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2207
    Prev
    Next
    INDEX
    Explanations

    coding components and functions related to UI and data management in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.79
    audiovisuel
    -0.66
    UserScript
    -0.64
    styleType
    -0.64
    parsedMessage
    -0.63
    ViewImports
    -0.62
     setEmail
    -0.61
    protoimpl
    -0.60
     Italijani
    -0.60
     uLocal
    -0.58
    POSITIVE LOGITS
     discriminación
    0.38
     geprek
    0.37
     common
    0.35
     fine
    0.35
     sør
    0.35
    endregion
    0.34
    닙
    0.34
     plain
    0.34
     very
    0.33
     only
    0.33
    Activations Density 0.156%

    No Known Activations