© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5439
    Prev
    Next
    INDEX
    Explanations

    concepts related to mathematical functions, specifically in the context of statistical coefficients and gamma functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.55
     snippetHide
    -0.47
     שוליים
    -0.46
    httphttps
    -0.46
    SOUNDBITE
    -0.46
     ✭✭
    -0.45
     fieldNum
    -0.43
    TokenNameLBRACE
    -0.41
    Referències
    -0.40
    postsleuth
    -0.40
    POSITIVE LOGITS
     AssemblyCompany
    0.51
     philo
    0.44
    +#+
    0.44
    binom
    0.42
     FIB
    0.41
    ftagPool
    0.41
    戬
    0.41
    
    0.41
     phil
    0.40
     CAI
    0.39
    Activations Density 1.354%

    No Known Activations