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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13470
    Prev
    Next
    INDEX
    Explanations

    technical terms related to medical and scientific instruments and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical descriptions that highlight advantages or benefits of a method or device.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    lists or enumerations of advantages and benefits, especially when formatted with commas between items.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    descriptions of advantages and benefits of methods or systems.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     försö
    -0.43
     unsuccessfully
    -0.42
     insufic
    -0.40
    nadequate
    -0.40
    足りない
    -0.38
    pflich
    -0.38
    świad
    -0.38
    才會
    -0.37
     leider
    -0.37
    temming
    -0.36
    POSITIVE LOGITS
     easy
    1.08
     inexpensive
    1.04
     easily
    0.99
    easy
    0.95
     ease
    0.88
     simplicity
    0.88
     fácil
    0.87
    easily
    0.86
     łat
    0.84
    Easy
    0.84
    Activations Density 0.875%

    No Known Activations