© 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. 33-GEMMASCOPE-RES-16K
    11. 2564
    Prev
    Next
    INDEX
    Explanations

    numerical values or statistical results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kháu
    -0.66
    mybatisplus
    -0.63
    Datuak
    -0.54
     Infórmanos
    -0.53
    SpringBootTest
    -0.53
    batore
    -0.52
    sendRedirect
    -0.49
     Autorizaciones
    -0.49
    "+
    -0.49
    ]}"
    -0.49
    POSITIVE LOGITS
    ClientSize
    0.36
    AnchorStyles
    0.30
     Provin
    0.29
     POP
    0.28
    kost
    0.27
    ToMap
    0.27
    wapV
    0.26
     arşivlendi
    0.26
    ల్ల
    0.26
     joaat
    0.25
    Activations Density 0.572%

    No Known Activations