© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5970
    Prev
    Next
    INDEX
    Explanations

    references to social hierarchies and dynamics, particularly involving race

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    cultural dominance and genetics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Currently
    -0.54
     currently
    -0.54
    Currently
    -0.53
    drew
    -0.52
    췄
    -0.52
     betweenstory
    -0.51
     drew
    -0.49
    currently
    -0.48
     geçti
    -0.47
    Predecesor
    -0.46
    POSITIVE LOGITS
     usually
    1.12
     often
    1.04
    usually
    0.96
     typically
    0.94
     biasanya
    0.92
     Usually
    0.92
    Usually
    0.91
     Often
    0.90
     souvent
    0.89
    often
    0.89
    Activations Density 0.932%

    No Known Activations