© 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 - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 14791
    Prev
    Next
    INDEX
    Explanations

    the word "brilliant" and related expressions of excellence or praise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schild
    -0.41
     wack
    -0.40
     slow
    -0.38
    odore
    -0.36
    lauf
    -0.36
    mologie
    -0.35
    浅
    -0.35
     регу
    -0.35
    tagHelperRunner
    -0.35
     proche
    -0.35
    POSITIVE LOGITS
     HttpNotFound
    0.59
    migrationBuilder
    0.57
    EFIAPI
    0.55
     ISNI
    0.54
     zijne
    0.53
    expandindo
    0.51
    GeneratedMessage
    0.50
     universally
    0.50
     Италијани
    0.50
    CodedInputStream
    0.49
    Activations Density 0.134%

    No Known Activations