© 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. 6348
    Prev
    Next
    INDEX
    Explanations

    numeric sequences and statistical references in scientific writing

    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
     Kompon
    -0.41
     itself
    -0.36
     yet
    -0.35
    zuführen
    -0.33
    –
    -0.31
    sieren
    -0.31
    कर्
    -0.30
    RTLI
    -0.29
     contributions
    -0.29
    ced
    -0.28
    POSITIVE LOGITS
     гг
    0.90
     HasFactory
    0.85
     inclusive
    0.82
    NUMX
    0.80
    TargetException
    0.75
    inclusive
    0.73
     disambiguazione
    0.70
    不等
    0.70
    にかけて
    0.64
     autorytatywna
    0.64
    Activations Density 1.469%

    No Known Activations