© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101742
    Prev
    Next
    INDEX
    Explanations

    discourse focused on the complexities of social and legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蚪
    -0.52
    inheritDoc
    -0.52
     disambiguazione
    -0.52
    tagHelperRunner
    -0.46
    EndGlobalSection
    -0.46
    migrationBuilder
    -0.46
    IUrlHelper
    -0.45
    fromnode
    -0.44
    #+#
    -0.43
     raisonnable
    -0.43
    POSITIVE LOGITS
    UMBIA
    0.38
     regrettable
    0.38
     traverse
    0.38
     Lokales
    0.37
     Wilkes
    0.37
     unsatisfactory
    0.36
     Coleridge
    0.36
    lccn
    0.36
     spill
    0.35
     caratteri
    0.35
    Activations Density 0.069%

    No Known Activations