© 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. 23-GEMMASCOPE-RES-16K
    11. 10650
    Prev
    Next
    INDEX
    Explanations

    numerical values and their organization within contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſei
    -0.88
    migrationBuilder
    -0.88
     laſſen
    -0.84
     betweenstory
    -0.84
    Tikang
    -0.84
     queſta
    -0.83
    uxxxx
    -0.83
     zuſammen
    -0.81
    ésultats
    -0.79
     geſch
    -0.79
    POSITIVE LOGITS
    2
    0.36
    3
    0.31
    5
    0.30
    GetNext
    0.28
    1
    0.27
     agrav
    0.26
     Others
    0.26
    6
    0.26
    nivå
    0.25
    0
    0.25
    Activations Density 2.340%

    No Known Activations