© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 11239
    Prev
    Next
    INDEX
    Explanations

    numerical values and legal citations related to court cases

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

    legal codes/citations

    np_acts-logits-general · gemini-2.0-flash

    legal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.66
     (
    -0.57
    r
    -0.57
     and
    -0.56
      
    -0.56
    ↵↵
    -0.56
    ↵
    -0.55
     r
    -0.54
     "
    -0.54
     c
    -0.53
    POSITIVE LOGITS
     myſelf
    1.23
     Anſ
    1.14
     ―――――
    1.11
     raiſ
    1.10
     pleaſure
    1.08
     iſt
    1.08
     itſelf
    1.08
     Monfieur
    1.08
     ſeveral
    1.06
     Jefus
    1.05
    Activations Density 0.483%

    No Known Activations