© 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. 15-GEMMASCOPE-RES-16K
    11. 1989
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal reasoning and the interpretation of statutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.67
    posedge
    -0.58
    excell
    -0.52
    validates
    -0.51
    ц
    -0.48
    PerformLayout
    -0.48
    RefNanny
    -0.47
    #
    -0.47
     saja
    -0.47
    :]:
    -0.46
    POSITIVE LOGITS
     intended
    1.23
     intent
    1.14
    intended
    1.10
     Intended
    1.04
     intention
    0.99
     intentions
    0.96
     tarko
    0.95
    intent
    0.94
     Intent
    0.91
    Intent
    0.89
    Activations Density 0.633%

    No Known Activations