© 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. 40-GEMMASCOPE-RES-16K
    11. 3334
    Prev
    Next
    INDEX
    Explanations

    quotes and attributes related to layout properties and dimensions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Heads
    -0.99
    Heads
    -0.91
     Holds
    -0.89
     Hands
    -0.87
    Has
    -0.86
     Hypers
    -0.84
     Has
    -0.84
    Hands
    -0.83
    HAND
    -0.83
    HAS
    -0.83
    POSITIVE LOGITS
     הה
    0.61
     اله
    0.45
     h
    0.44
     hora
    0.44
     hã
    0.41
     hall
    0.40
     һ
    0.40
     hell
    0.39
     het
    0.39
     halı
    0.39
    Activations Density 1.241%

    No Known Activations