© 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. 15133
    Prev
    Next
    INDEX
    Explanations

    terms related to fluid dynamics and printing technology

    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
    windowFixed
    -0.57
     виправивши
    -0.51
    Kariera
    -0.49
    󠁢
    -0.49
    RTLI
    -0.46
    
    -0.44
    Elliott
    -0.44
    oa̍t
    -0.44
    NSE
    -0.44
     vPvB
    -0.43
    POSITIVE LOGITS
     jet
    0.71
     din
    0.66
     dyna
    0.61
     Jet
    0.61
     Din
    0.60
    ire
    0.59
     dynamic
    0.57
    Din
    0.57
     dinámico
    0.56
    ect
    0.56
    Activations Density 0.541%

    No Known Activations