© 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. 31-GEMMASCOPE-RES-16K
    11. 1919
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in data sets, indicating systems or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hexadecimal numbers and numeric constants in code and system output.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    -0.79
    en
    -0.66
    Autoritní
    -0.65
    esis
    -0.58
    rungsseite
    -0.57
    erol
    -0.56
    enis
    -0.56
     Nunez
    -0.56
    ING
    -0.55
    eson
    -0.54
    POSITIVE LOGITS
    4
    0.84
     quatrième
    0.52
     Meksiku
    0.52
     AssemblyCompany
    0.49
    cientos
    0.45
     cuarenta
    0.45
     czter
    0.45
     Fourth
    0.44
    atrième
    0.43
    Empereur
    0.43
    Activations Density 1.268%

    No Known Activations