© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5866
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming, game development, and system design

    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
    цездатний
    -0.44
    StoreMessageInfo
    -0.44
    
    -0.41
    Hozzáférés
    -0.40
    PreInfinity
    -0.38
    IMPORTED
    -0.35
    WithMany
    -0.35
     TextAppearance
    -0.35
    bürger
    -0.33
     Swe
    -0.33
    POSITIVE LOGITS
     wise
    2.94
    wise
    2.67
    Wise
    2.13
     Wise
    2.11
    WISE
    2.05
     WISE
    1.97
     wisest
    1.53
     wiser
    1.46
     wisdom
    1.24
     wisely
    1.20
    Activations Density 0.296%

    No Known Activations