© 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. 8120
    Prev
    Next
    INDEX
    Explanations

    references to academic programs and their attributes

    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
     Dial
    -0.55
    Dialog
    -0.54
     Displacement
    -0.54
     Domain
    -0.54
     Disclosure
    -0.54
     Drain
    -0.53
    Discovery
    -0.53
     Difference
    -0.53
     Discount
    -0.52
     Distribution
    -0.52
    POSITIVE LOGITS
     des
    1.14
     DES
    1.05
     Des
    1.02
    des
    0.96
    Des
    0.96
    DES
    0.87
     Desmond
    0.85
     deſ
    0.84
     デ
    0.84
     desi
    0.83
    Activations Density 1.625%

    No Known Activations