© 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. 7-GEMMASCOPE-RES-16K
    11. 13391
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "something" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIAF
    -0.40
     anzuzeigen
    -0.39
    flüs
    -0.38
    ☑
    -0.38
     oč
    -0.38
     grid
    -0.37
     Grid
    -0.37
    Grid
    -0.36
     grids
    -0.36
    caloosa
    -0.36
    POSITIVE LOGITS
     something
    2.39
    Something
    2.22
    something
    2.20
     Something
    2.17
     SOMETHING
    1.91
     somethin
    1.77
     quelque
    1.38
     qualcosa
    1.33
     iets
    1.32
     somewhere
    1.29
    Activations Density 0.085%

    No Known Activations