© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 14837
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and queries indicating action or requests for assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Exactos
    -0.61
    RegistryLite
    -0.61
     păr
    -0.60
    UnusedPrivate
    -0.57
     înal
    -0.56
     økonom
    -0.55
    onOptions
    -0.54
     ostensibly
    -0.54
    EndGlobalSection
    -0.53
    FlowLayout
    -0.53
    POSITIVE LOGITS
     able
    0.70
     fulfill
    0.68
     fulfil
    0.67
     aware
    0.64
     solve
    0.62
     gonna
    0.61
     oprot
    0.59
     prouve
    0.58
     survie
    0.56
     save
    0.56
    Activations Density 0.530%

    No Known Activations