© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 14817
    Prev
    Next
    INDEX
    Explanations

    instances of engagement or commitment-related actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
     douceur
    -0.56
     sixties
    -0.49
    Eloquent
    -0.48
    mitz
    -0.47
    ByDate
    -0.47
    vaded
    -0.47
     six
    -0.47
    lijken
    -0.47
    enski
    -0.45
    PasswordEncoder
    -0.45
    POSITIVE LOGITS
    AddTagHelper
    0.67
     OFDb
    0.59
    migrationBuilder
    0.54
     שוליים
    0.53
    elemField
    0.53
    CloseOperation
    0.51
     jScrollPane
    0.50
     AssemblyCulture
    0.50
    AndEndTag
    0.48
    новништво
    0.47
    Activations Density 0.249%

    No Known Activations