© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1278
    Prev
    Next
    INDEX
    Explanations

    references to religious beliefs and their intersection with laws and regulations

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

    language related to religious beliefs and their impact on legislation

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

    rights and refusal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.70
    alamus
    -0.65
    principalTable
    -0.61
     برانيه
    -0.60
    matchCondition
    -0.58
    ymce
    -0.57
    iotensin
    -0.57
    Succ
    -0.56
     typelib
    -0.54
    CppMethod
    -0.53
    POSITIVE LOGITS
     unvaccinated
    0.92
     refusal
    0.81
     refus
    0.77
     Vaccine
    0.75
     refuser
    0.74
     refusing
    0.74
     vaccine
    0.74
     conspiracy
    0.69
     conspira
    0.66
     oppos
    0.65
    Activations Density 0.079%

    No Known Activations