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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 7369
    Prev
    Next
    INDEX
    Explanations

    specific variable or parameter definitions within programming or technical documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.73
    :✨
    -0.69
    RegressionTest
    -0.64
     EconPapers
    -0.60
    CloseOperation
    -0.59
     برانيه
    -0.59
    UserScript
    -0.58
    RefNanny
    -0.57
    expandindo
    -0.57
    +#+#
    -0.57
    POSITIVE LOGITS
     represents
    0.64
     used
    0.63
     specifies
    0.55
     hvilken
    0.55
     optional
    0.55
     refers
    0.55
     vilken
    0.54
     denotes
    0.53
     defines
    0.53
     representing
    0.53
    Activations Density 0.506%

    No Known Activations