© 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. 15916
    Prev
    Next
    INDEX
    Explanations

    the function or purpose of something described in the text

    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
     ſtate
    -0.97
     purpoſe
    -0.96
     ſta
    -0.93
     houſe
    -0.88
     ſche
    -0.88
     itſelf
    -0.84
     raiſ
    -0.82
     anſ
    -0.82
     faſt
    -0.81
     ſte
    -0.80
    POSITIVE LOGITS
     for
    1.24
    for
    0.78
     für
    0.77
     untuk
    0.76
     For
    0.71
     voor
    0.71
     για
    0.70
     pentru
    0.70
     برای
    0.69
    For
    0.66
    Activations Density 0.508%

    No Known Activations