© 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. 33-GEMMASCOPE-RES-16K
    11. 7466
    Prev
    Next
    INDEX
    Explanations

    indicators of user input and customization in a digital context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.75
     ſeveral
    -0.65
     ſche
    -0.63
     méri
    -0.63
    belong
    -0.62
     fubject
    -0.60
     quæ
    -0.59
     kasarigan
    -0.59
     appartiennent
    -0.59
     Monfieur
    -0.58
    POSITIVE LOGITS
     selectively
    0.50
     actively
    0.50
     forcefully
    0.46
     forcibly
    0.45
     take
    0.44
     make
    0.42
     активно
    0.42
     give
    0.41
    把
    0.41
    JoinColumn
    0.40
    Activations Density 0.003%

    No Known Activations