© 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. 6-GEMMASCOPE-RES-16K
    11. 13049
    Prev
    Next
    INDEX
    Explanations

    discussions about legal evidence, testimony, and claims of innocence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    älde
    -0.52
    enumii
    -0.51
     Particular
    -0.51
    StatusCodes
    -0.50
    mentos
    -0.50
    sidemargin
    -0.49
    ekan
    -0.49
    eter
    -0.48
    ioca
    -0.47
    pois
    -0.47
    POSITIVE LOGITS
     ویکی‌پدی
    0.71
     pourtant
    0.66
     preuves
    0.60
     délib
    0.59
    明明
    0.58
     муніципалі
    0.58
     AssemblyCulture
    0.57
     unknownFields
    0.56
     begged
    0.54
     elefante
    0.54
    Activations Density 1.112%

    No Known Activations