© 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. 3-GEMMASCOPE-RES-16K
    11. 10930
    Prev
    Next
    INDEX
    Explanations

    the keyword "let" in programming-related contexts, indicating variable declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.51
    zaamheid
    -0.42
    الحياه
    -0.41
    BackStack
    -0.41
     døde
    -0.39
     ſur
    -0.38
     musikk
    -0.37
    存于互联网档案馆
    -0.36
     quæ
    -0.36
     slutt
    -0.36
    POSITIVE LOGITS
    let
    3.67
    LET
    2.38
    lets
    2.27
     let
    1.87
    LETS
    1.73
    lete
    1.45
    letting
    1.41
    lette
    1.37
    lett
    1.35
     LET
    1.35
    Activations Density 0.079%

    No Known Activations