© 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. 34-GEMMASCOPE-RES-16K
    11. 513
    Prev
    Next
    INDEX
    Explanations

    instances of the words "though" and "although" indicating contrast or concession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.69
    SequentialGroup
    -0.68
    RuleContext
    -0.67
    AddTagHelper
    -0.60
    PerformLayout
    -0.59
     purpoſe
    -0.59
     ویکی‌پدی
    -0.59
     NavController
    -0.58
    :✨
    -0.57
     Infórmanos
    -0.57
    POSITIVE LOGITS
     admittedly
    0.78
     they
    0.77
     technically
    0.68
     there
    0.65
     not
    0.64
     it
    0.60
     we
    0.58
    out
    0.57
     ironically
    0.54
     ideally
    0.53
    Activations Density 0.091%

    No Known Activations