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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 7194
    Prev
    Next
    INDEX
    Explanations

    amino acid names and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fusca
    -0.66
     الرياضيه
    -0.55
     CURLOPT
    -0.54
    OGND
    -0.53
    ValueStyle
    -0.51
    PhysRevD
    -0.49
     referenties
    -0.48
    TProtocol
    -0.48
    IsContent
    -0.47
     /\.
    -0.47
    POSITIVE LOGITS
    ########.
    0.84
     HasFactory
    0.53
     oprot
    0.53
    HomeAsUpEnabled
    0.52
    builtins
    0.50
     собі
    0.49
    AccessorTable
    0.48
    ódó
    0.48
     autorytatywna
    0.48
    脚注の使い方
    0.48
    Activations Density 0.434%

    No Known Activations