© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7581
    Prev
    Next
    INDEX
    Explanations

    programming function syntax and control flow structures

    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
    prepareStatement
    -0.47
    XtraReports
    -0.41
    tonsoft
    -0.39
    InputGroup
    -0.34
     ActivatedRoute
    -0.34
     Mond
    -0.33
     Metz
    -0.33
    gink
    -0.32
    localctx
    -0.31
    agte
    -0.31
    POSITIVE LOGITS
     len
    3.05
    len
    2.55
     Len
    2.48
    Len
    2.41
     LEN
    1.85
    LEN
    1.80
     lens
    1.34
     Lenny
    1.30
     Lenox
    1.25
     Lennox
    1.22
    Activations Density 0.296%

    No Known Activations