© 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. 2844
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal processes and evidence

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

    Text before citations/footnotes

    np_acts-logits-general · gemini-2.0-flash

    legal citations and terms

    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
    Whilst
    -1.17
     Whilst
    -1.16
    Firstly
    -0.94
    Anyways
    -0.93
     Amongst
    -0.93
     Firstly
    -0.92
     whilst
    -0.87
     Anyways
    -0.85
     تانيه
    -0.79
     anyways
    -0.78
    POSITIVE LOGITS
     quæ
    0.90
     auffi
    0.88
     eſſ
    0.88
     ་་
    0.82
    ​—
    0.81
     uſ
    0.79
     ainfi
    0.78
     vérit
    0.77
     ciasc
    0.75
     gewiß
    0.74
    Activations Density 1.570%

    No Known Activations