© 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. 18-GEMMASCOPE-RES-16K
    11. 6834
    Prev
    Next
    INDEX
    Explanations

    religious and ethnic identities or affiliations

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

    bias, preference, or favoring

    np_acts-logits-general · gemini-2.0-flash

    leaning or preference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.57
    hols
    -0.55
    ActivityResult
    -0.54
     cauſe
    -0.52
     Majefty
    -0.52
     Efq
    -0.49
     quæ
    -0.48
     אות
    -0.48
     diſt
    -0.48
     whoſe
    -0.47
    POSITIVE LOGITS
     leaning
    1.83
     leans
    1.68
     preference
    1.49
     lean
    1.49
    leaning
    1.41
     leaned
    1.41
     favoring
    1.40
     tendency
    1.38
     inclination
    1.37
    倾向
    1.36
    Activations Density 0.402%

    No Known Activations