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. 6249
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or terms related to technical processes and entities

    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
    webElementXpaths
    -0.73
    ⟬
    -0.69
     disambiguazione
    -0.62
     AssemblyCulture
    -0.59
    Билгалдахарш
    -0.58
    лтамалар
    -0.58
    hyrchwyd
    -0.53
     AssemblyTitle
    -0.53
     Biôgrafia
    -0.53
    msgTypes
    -0.52
    POSITIVE LOGITS
    mittee
    0.37
     sal
    0.36
     Sah
    0.35
     BAC
    0.32
     specialist
    0.32
     Friday
    0.32
     stick
    0.32
     weh
    0.32
    UserDao
    0.32
     Specialists
    0.31
    Activations Density 1.193%

    No Known Activations