© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 56294
    Prev
    Next
    INDEX
    Explanations

    terms related to legal evidence and admissibility in court

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.62
    sendRedirect
    -0.59
    IGO
    -0.55
    orst
    -0.55
    исленность
    -0.55
    ziz
    -0.54
    avir
    -0.54
    SBATCH
    -0.54
    cile
    -0.54
    etto
    -0.53
    POSITIVE LOGITS
    GEBURTSDATUM
    0.60
    ностран
    0.55
     testimony
    0.55
     nationales
    0.52
     testified
    0.51
     مباش
    0.50
     subpoena
    0.50
     witness
    0.50
     witnesses
    0.50
     indirect
    0.50
    Activations Density 0.401%

    No Known Activations