© 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. 1270
    Prev
    Next
    INDEX
    Explanations

    references to processes or actions related to handling or manipulating files and data

    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
     Administrativna
    -0.60
     lenker
    -0.53
    DIPSETTING
    -0.52
    setVerticalGroup
    -0.50
     defStyleAttr
    -0.49
    ="@+
    -0.47
    PreferredItem
    -0.46
    terase
    -0.46
     Мексичка
    -0.45
    transQ
    -0.44
    POSITIVE LOGITS
     drop
    4.06
     Drop
    3.78
    Drop
    3.58
     dropped
    3.56
     drops
    3.55
    drop
    3.52
     dropping
    3.50
     DROP
    3.31
     Drops
    3.16
     Dro
    3.06
    Activations Density 0.710%

    No Known Activations