© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9303
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "pk" and its variants in text, likely related to primary keys in database contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ódź
    -0.77
     sanitarias
    -0.71
     déclar
    -0.70
    =$?
    -0.70
    msgTypes
    -0.69
     ImportError
    -0.68
     onBackPressed
    -0.68
    LookAnd
    -0.67
     păr
    -0.67
     gainera
    -0.65
    POSITIVE LOGITS
    pk
    0.79
    PK
    0.62
     pk
    0.60
    mathbf
    0.57
    Pk
    0.53
    andag
    0.50
     Fra
    0.50
    nsic
    0.49
    photobucket
    0.49
     προς
    0.49
    Activations Density 0.106%

    No Known Activations