© 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. 37-GEMMASCOPE-RES-16K
    11. 5917
    Prev
    Next
    INDEX
    Explanations

    letters and their combinations in a statistical or probabilistic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -1.13
     Chwiliwch
    -1.11
    httphttps
    -1.08
     nahilalakip
    -1.03
     surla
    -1.01
    InjectAttribute
    -1.00
     resourceCulture
    -0.96
    rungsseite
    -0.95
    IUrlHelper
    -0.95
    tagHelperRunner
    -0.94
    POSITIVE LOGITS
    g
    0.50
    is
    0.47
    b
    0.46
    l
    0.45
    m
    0.45
    i
    0.45
    ?
    0.44
    .
    0.44
    c
    0.44
    d
    0.43
    Activations Density 1.222%

    No Known Activations