© 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. 27-GEMMASCOPE-RES-16K
    11. 8546
    Prev
    Next
    INDEX
    Explanations

    phrases related to arguments and claims in legal or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jewództ
    -0.53
     JpaRepository
    -0.51
    ClientSize
    -0.50
    __*/
    -0.46
    сылкі
    -0.45
     Cedex
    -0.45
     WaitForSeconds
    -0.45
    たまた
    -0.45
    fromCharCode
    -0.44
    licola
    -0.44
    POSITIVE LOGITS
     three
    0.91
     two
    0.83
     folgendes
    0.74
     följande
    0.70
     seguintes
    0.70
     folgende
    0.68
     trois
    0.66
    三個
    0.66
    三个
    0.65
     folgender
    0.64
    Activations Density 0.730%

    No Known Activations