© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 14974
    Prev
    Next
    INDEX
    Explanations

    terms related to power dynamics and privilege in societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ParallelGroup
    -0.54
    UTERS
    -0.52
    ​—
    -0.51
    整
    -0.48
    ATILE
    -0.48
    hintText
    -0.48
    httphttps
    -0.47
    ']>;
    -0.46
     isKindOfClass
    -0.46
    pensive
    -0.46
    POSITIVE LOGITS
     monopoly
    0.73
     seniority
    0.64
    CloseOperation
    0.63
     creen
    0.62
     privilege
    0.61
     monopol
    0.61
     privileged
    0.61
     Monopoly
    0.58
    AccessorTable
    0.57
    glPushMatrix
    0.56
    Activations Density 0.324%

    No Known Activations