© 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. 41-GEMMASCOPE-RES-16K
    11. 7537
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to algorithm complexity and computational processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ferous
    -0.38
     toxicology
    -0.37
     Deere
    -0.36
     vVar
    -0.35
     Zat
    -0.35
     tube
    -0.34
     juice
    -0.34
     Geschw
    -0.34
    trus
    -0.34
    ModelAdmin
    -0.34
    POSITIVE LOGITS
     algorithm
    0.95
     Algorithm
    0.87
    Algorithm
    0.84
    algorithm
    0.81
     algoritmo
    0.80
    算法
    0.80
    GORITHM
    0.78
     algorit
    0.77
     алгорит
    0.75
     algorithms
    0.73
    Activations Density 1.252%

    No Known Activations