© 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. 1-GEMMASCOPE-RES-16K
    6. 6783
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to rights and discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spirituale
    -0.74
     Monfieur
    -0.73
     himſelf
    -0.72
     habet
    -0.71
     Dumnezeu
    -0.71
     Shakspeare
    -0.70
     myſelf
    -0.68
     siguran
    -0.68
     anún
    -0.68
     themſelves
    -0.68
    POSITIVE LOGITS
    tagHelperRunner
    0.93
    ValueStyle
    0.82
    JspWriter
    0.81
    "):
    
    0.74
    ())),
    0.72
    ")),
    0.72
     surla
    0.70
     дописавши
    0.70
     مرئيه
    0.69
    '])->
    0.69
    Activations Density 0.507%

    No Known Activations