© 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. 40-GEMMASCOPE-RES-16K
    11. 1721
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and functions, particularly for parameter handling and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    directories
    -0.61
     Normdatei
    -0.57
    closures
    -0.54
    repositories
    -0.53
    Sequences
    -0.52
    committees
    -0.52
    parameters
    -0.51
     Societies
    -0.51
     antibodies
    -0.51
    boundaries
    -0.51
    POSITIVE LOGITS
     cams
    0.82
     sims
    0.80
     mins
    0.76
    sims
    0.75
     amps
    0.75
    Sims
    0.74
     Sims
    0.74
     sams
    0.70
    ams
    0.69
     Sams
    0.69
    Activations Density 0.969%

    No Known Activations