© 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. 14015
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or highlights within a narrative or discussion

    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
     język
    -0.50
     plufieurs
    -0.46
     ogranic
    -0.45
     juridiques
    -0.45
     zarządz
    -0.45
    Życiorys
    -0.44
     leren
    -0.43
     umożli
    -0.43
     nadzie
    -0.43
     uzyska
    -0.42
    POSITIVE LOGITS
     spot
    3.27
    spot
    2.97
     Spot
    2.94
    Spot
    2.88
     spots
    2.66
     SPOT
    2.61
    spots
    2.45
     Spots
    2.41
    SPOT
    2.38
    Spots
    2.27
    Activations Density 0.076%

    No Known Activations