© 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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 8522
    Prev
    Next
    INDEX
    Explanations

    references to legal and procedural terms, particularly in relation to case law and court systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gorg
    -1.06
    IBOutlet
    -1.03
    NegativeButton
    -1.02
     protoimpl
    -1.01
    entile
    -1.00
    protoimpl
    -1.00
     متعلقه
    -1.00
     שוליים
    -0.98
    EndInit
    -0.97
    InputTagHelper
    -0.95
    POSITIVE LOGITS
    Cree
    0.88
     Cree
    0.86
     Moos
    0.80
     Mee
    0.71
    cree
    0.70
     Booth
    0.70
    chaik
    0.69
    знача
    0.67
     Steen
    0.66
     tear
    0.65
    Activations Density 2.491%

    No Known Activations