© 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. 2-GEMMASCOPE-RES-16K
    11. 5433
    Prev
    Next
    INDEX
    Explanations

    instances of the word "compelling" and related terms indicating strong interest or engagement

    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
    #+#
    -0.69
     Exactos
    -0.63
     CanadaChoose
    -0.56
    SourceChecksum
    -0.56
    ChildScrollView
    -0.56
    EndGlobalSection
    -0.56
    RTDA
    -0.54
    dafx
    -0.53
     indisponible
    -0.53
    HasAnnotation
    -0.52
    POSITIVE LOGITS
     compelling
    2.08
     captivating
    1.43
     alluring
    1.28
     persuasive
    1.27
     enticing
    1.23
     appealing
    1.19
     intriguing
    1.19
     fascinating
    1.15
     convincing
    1.13
     seductive
    1.12
    Activations Density 0.390%

    No Known Activations