© 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. 7-GEMMASCOPE-RES-16K
    6. 1971
    Prev
    Next
    INDEX
    Explanations

    references to historical analysis and discussions related to race

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abestanden
    -1.02
    DockStyle
    -0.79
    SharedDtor
    -0.77
    Rujuakan
    -0.77
     InputDecoration
    -0.74
     esternos
    -0.70
     indisponible
    -0.68
     Houſe
    -0.66
     houſe
    -0.66
     Roskov
    -0.65
    POSITIVE LOGITS
     historians
    0.84
     Geschichts
    0.76
     history
    0.75
     History
    0.74
     historical
    0.73
     historian
    0.71
     histor
    0.70
     Historical
    0.67
    historical
    0.67
     sejarah
    0.66
    Activations Density 0.331%

    No Known Activations