© 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. 523
    Prev
    Next
    INDEX
    Explanations

    programming syntax structures, particularly related to code blocks and delimiters

    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
    enumi
    -0.74
    ValueStyle
    -0.71
    uxxxx
    -0.65
    enumii
    -0.62
    sidemargin
    -0.61
    AnimationsModule
    -0.59
     otomatig
    -0.57
     kasarigan
    -0.57
    تقاوى
    -0.56
    ंदीखरीदारी
    -0.55
    POSITIVE LOGITS
     CURIAM
    0.45
    الحياه
    0.40
     berat
    0.38
     teras
    0.32
     récomp
    0.32
    락
    0.32
    ıldız
    0.32
    geving
    0.32
    ❋
    0.32
    medskip
    0.31
    Activations Density 0.202%

    No Known Activations