© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15724
    Prev
    Next
    INDEX
    Explanations

    statements or arguments made in discussions

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

    sentences that make or emphasize a central argument or conclusion.

    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
    FromArgb
    -0.37
    ंज
    -0.35
     Amts
    -0.35
    Pragma
    -0.34
     eş
    -0.34
     Zeug
    -0.34
     Einf
    -0.33
     ори
    -0.32
     Schuster
    -0.31
    альное
    -0.31
    POSITIVE LOGITS
     point
    2.16
    point
    1.68
     Point
    1.65
     POINT
    1.62
    Point
    1.58
     punto
    1.45
    POINT
    1.45
    getPoint
    1.13
    punto
    1.13
     points
    1.08
    Activations Density 0.305%

    No Known Activations