© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-GEMMASCOPE-RES-16K
    11. 4392
    Prev
    Next
    INDEX
    Explanations

    titles or positions related to leadership or authority, particularly those involving the term "Chief."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
     Pilate
    -0.66
     Chwiliwch
    -0.65
    adering
    -0.59
    ECC
    -0.59
    Rüyada
    -0.58
     Mesmo
    -0.55
     שוליים
    -0.53
     Trotzdem
    -0.52
    derry
    -0.52
     dressing
    -0.52
    POSITIVE LOGITS
     Chief
    3.59
    Chief
    3.51
     chief
    3.46
     CHIEF
    3.26
    chief
    3.14
     chiefs
    2.48
     Chiefs
    2.35
    chiefs
    2.06
    首席
    1.75
     chefe
    1.58
    Activations Density 0.073%

    No Known Activations