© 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. 38-GEMMASCOPE-RES-16K
    11. 12522
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to systems, measurements, and parameters in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gave
    -0.58
     myſelf
    -0.57
     didst
    -0.57
     offers
    -0.56
    にしました
    -0.55
    offers
    -0.55
     позволит
    -0.55
    提供了
    -0.55
    使用了
    -0.54
     recommends
    -0.53
    POSITIVE LOGITS
     becomes
    1.29
     gets
    1.12
     goes
    1.08
     disappears
    1.07
     begins
    1.07
     ceases
    1.00
     emerges
    0.98
     Becomes
    0.98
    becomes
    0.98
     arrives
    0.97
    Activations Density 1.276%

    No Known Activations