© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 12279
    Prev
    Next
    INDEX
    Explanations

    terms related to advantages and features of technology or devices

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

    lists of product features or advantages, especially those describing something as easy, convenient, or flexible.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    جمعیت
    -0.48
     chi̍t
    -0.45
    WriteBarrier
    -0.45
     Exacts
    -0.45
    farin
    -0.44
     pri
    -0.43
    getMenuInflater
    -0.42
     Royal
    -0.41
    fangen
    -0.40
    caught
    -0.40
    POSITIVE LOGITS
    يكب
    0.51
    Easier
    0.46
     Mudah
    0.45
     arbejds
    0.43
     Vorteil
    0.43
     faciles
    0.42
     fácil
    0.41
    Easy
    0.41
     easy
    0.41
     Easy
    0.40
    Activations Density 1.061%

    No Known Activations