© 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. 9228
    Prev
    Next
    INDEX
    Explanations

    references to leadership positions or locations related to a 'head' or 'headquarters'

    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
     referenties
    -0.48
    silien
    -0.46
    ,
    -0.45
    よう
    -0.41
     cour
    -0.41
    Utf
    -0.40
    atie
    -0.40
    web
    -0.39
     caos
    -0.39
    Step
    -0.39
    POSITIVE LOGITS
    tagHelperRunner
    1.17
     head
    1.09
     Heads
    1.08
     heads
    1.06
    heads
    1.02
    Headquarters
    1.02
     Headquarters
    1.01
     headquarters
    1.00
     HEAD
    0.94
     Head
    0.93
    Activations Density 0.258%

    No Known Activations