Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1074
    Prev
    Next
    INDEX
    Explanations

    references to legal codes and statutory information

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

    Louisiana legal references

    np_acts-logits-general · gemini-2.0-flash

    Louisiana places and legal citations

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    RuleContext
    -0.66
    oredCriteria
    -0.54
    下载附件
    -0.52
    ngdoc
    -0.52
     MainAxisSize
    -0.51
    anyahu
    -0.51
    Geplaatst
    -0.50
    المكان
    -0.49
    ništ
    -0.49
    UnsafeEnabled
    -0.46
    POSITIVE LOGITS
     Louisiana
    1.31
    Louisiana
    1.21
     Bayou
    1.05
     Mardi
    1.02
     Cajun
    1.02
     Tulane
    0.99
     LSU
    0.98
     Baton
    0.97
     Parish
    0.95
     parish
    0.94
    Activations Density 0.227%

    No Known Activations