© 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. 2-GEMMASCOPE-RES-16K
    11. 2246
    Prev
    Next
    INDEX
    Explanations

    references to shelves and related terminology in various contexts

    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
    almaz
    -0.47
    extAlignment
    -0.46
    </tfoot>
    -0.45
    _^
    -0.44
    tagext
    -0.43
    __':
    -0.42
     AssemblyCompany
    -0.42
     Thors
    -0.41
     Winaray
    -0.41
    IVersion
    -0.41
    POSITIVE LOGITS
     rack
    0.74
     shelf
    0.73
     Shelf
    0.71
     racks
    0.70
     shelves
    0.70
    Shelf
    0.62
     hung
    0.60
     Shelves
    0.59
    shelf
    0.59
    Rack
    0.58
    Activations Density 0.748%

    No Known Activations