© 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. 3-GEMMASCOPE-RES-16K
    11. 15941
    Prev
    Next
    INDEX
    Explanations

    mentions of legal cases and case management terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.41
     Theſe
    -1.23
     raiſ
    -1.17
     pleaſure
    -1.15
     Efq
    -1.11
     Eſ
    -1.09
     uſed
    -1.02
     myſelf
    -1.02
     Majefty
    -1.01
     ſmall
    -1.00
    POSITIVE LOGITS
     case
    3.31
     Case
    3.00
    Case
    2.92
    case
    2.91
     cases
    2.79
     CASE
    2.76
    CASE
    2.60
     Cases
    2.54
    Cases
    2.41
    cases
    2.40
    Activations Density 0.095%

    No Known Activations