© 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. 8-GEMMASCOPE-RES-16K
    11. 2220
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups, particularly in the context of judgment or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wilber
    -0.85
    ocarp
    -0.81
     écou
    -0.78
    laps
    -0.76
    Nag
    -0.73
     Mep
    -0.72
     MEG
    -0.70
     SNA
    -0.69
     Fascism
    -0.69
     Nag
    -0.69
    POSITIVE LOGITS
     those
    1.60
    Those
    1.37
    those
    1.35
     Those
    1.32
     THOSE
    1.16
     who
    1.12
     ceux
    1.07
     aquellos
    1.03
    那些
    0.95
     aqueles
    0.95
    Activations Density 0.081%

    No Known Activations