© 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. 3-GEMMASCOPE-RES-16K
    11. 9545
    Prev
    Next
    INDEX
    Explanations

    references to academic articles or terminology related to statistics and estimation methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quæ
    -0.43
    gjenge
    -0.38
    engaruhi
    -0.38
     Preguntas
    -0.35
     ägg
    -0.35
     schia
    -0.33
     eſt
    -0.33
     håll
    -0.33
     ejus
    -0.33
     rispet
    -0.32
    POSITIVE LOGITS
    als
    2.00
    ALS
    1.66
    ls
    1.36
    LS
    1.26
    els
    1.25
     Als
    1.23
    Als
    1.21
    ELS
    1.14
     als
    1.12
     ls
    1.09
    Activations Density 1.052%

    No Known Activations