© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 10520
    Prev
    Next
    INDEX
    Explanations

    discussions regarding components or aspects of legal proceedings and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.54
     otomatig
    -0.51
     guangdong
    -0.49
    Boxscore
    -0.48
    Véxase
    -0.46
     flush
    -0.44
    ectoria
    -0.43
    格
    -0.43
    enumi
    -0.43
    Handlung
    -0.43
    POSITIVE LOGITS
     gewöhnlich
    0.51
     vainly
    0.50
     autrefois
    0.50
     früher
    0.47
     occasionally
    0.47
    Previously
    0.47
     previously
    0.46
     umgekehrt
    0.46
     Previously
    0.46
     künftig
    0.46
    Activations Density 0.408%

    No Known Activations