© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 8008
    Prev
    Next
    INDEX
    Explanations

    terms related to legal doctrines and principles of evidence

    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
     quæ
    -0.65
     origines
    -0.54
     passés
    -0.49
     poffe
    -0.49
     becauſe
    -0.48
     predecess
    -0.48
     origini
    -0.46
    værende
    -0.46
     himſelf
    -0.45
    v
    -0.45
    POSITIVE LOGITS
    onAttach
    0.97
    IsContent
    0.96
    rrggbb
    0.96
    LookAnd
    0.94
    ChildIndex
    0.92
     Roskov
    0.90
     defaultstate
    0.88
    XmlAccessType
    0.88
    UnusedPrivate
    0.85
    TintMode
    0.84
    Activations Density 1.556%

    No Known Activations