© 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. 40-GEMMASCOPE-RES-16K
    11. 5196
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific methods and measurements

    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
     disambiguazione
    -0.40
     المعيارى
    -0.37
    ⤹
    -0.34
    migrationBuilder
    -0.34
    ouvrage
    -0.29
    SequentialGroup
    -0.28
    alnız
    -0.27
    uisine
    -0.27
    ußt
    -0.27
    ソッド
    -0.26
    POSITIVE LOGITS
     EP
    1.54
     EB
    1.53
     EV
    1.46
     EG
    1.45
     EW
    1.42
     Eb
    1.41
     Ep
    1.41
     EC
    1.38
     EA
    1.38
     EK
    1.38
    Activations Density 3.501%

    No Known Activations