© 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. 5259
    Prev
    Next
    INDEX
    Explanations

    terms related to copyright and licensing

    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
     lenker
    -0.47
    TagMode
    -0.41
     <<<<<<<<<<<<<<
    -0.40
    utilisons
    -0.38
    ThroughAttribute
    -0.37
    ArrowToggle
    -0.36
    jsxFileName
    -0.35
    Rüyada
    -0.34
    مقاله
    -0.33
    Хьажоргаш
    -0.32
    POSITIVE LOGITS
     reserve
    3.77
     reserved
    3.45
     reserves
    3.33
     Reserve
    3.30
    Reserve
    3.19
    reserve
    3.13
     RESERVE
    3.05
     reserving
    3.03
     reserv
    3.02
     Reserved
    3.02
    Activations Density 0.499%

    No Known Activations