© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3385
    Prev
    Next
    INDEX
    Explanations

    key legal terms and phrases related to court proceedings and lawsuits

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

    phrases using "inter alia" or similar Latin legal phrases that introduce lists of examples.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xmlns
    -0.42
    fjspx
    -0.37
    amp
    -0.36
    BagLayout
    -0.35
    DockStyle
    -0.35
    ील
    -0.35
     ویکی‌پدی
    -0.35
    лю
    -0.34
    ostock
    -0.34
    そこは
    -0.34
    POSITIVE LOGITS
     among
    4.03
    among
    3.67
     amongst
    3.31
     Among
    3.14
     AMONG
    3.13
    Among
    3.02
     Amongst
    2.75
     parmi
    2.73
     среди
    2.66
     blandt
    2.50
    Activations Density 0.617%

    No Known Activations