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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 2858
    Prev
    Next
    INDEX
    Explanations

    references to individuals holding the title of "Chief" or similar high-ranking positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ECC
    -0.66
    <em>
    -0.62
     Trello
    -0.62
    rungsseite
    -0.61
    zeitung
    -0.59
    adering
    -0.58
     ECC
    -0.58
     trx
    -0.58
    pulos
    -0.56
    uncur
    -0.56
    POSITIVE LOGITS
     chief
    1.95
     CHIEF
    1.90
     Chief
    1.89
     Chiefs
    1.84
    Chief
    1.82
     chiefs
    1.74
    chief
    1.65
    chiefs
    1.47
    IEF
    1.12
    首席
    1.07
    Activations Density 0.039%

    No Known Activations