© 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. 1-GEMMASCOPE-RES-16K
    11. 6327
    Prev
    Next
    INDEX
    Explanations

    terms related to guest appearances and magical themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exécut
    -0.45
     executing
    -0.45
     Anspruch
    -0.41
     ladite
    -0.41
    ítmény
    -0.39
     purpoſe
    -0.38
    drawiam
    -0.37
    ateľ
    -0.35
     execution
    -0.35
    /***/
    -0.35
    POSITIVE LOGITS
     wonders
    1.11
    wonder
    1.09
     wonder
    1.05
    Wonder
    1.03
     miracle
    1.02
     Wonder
    1.02
     Wonders
    0.99
     magic
    0.92
     miracles
    0.91
    Magic
    0.87
    Activations Density 0.168%

    No Known Activations