© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 625
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "with."

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     ſte
    -0.91
     ſtate
    -0.91
     ſche
    -0.90
     ſta
    -0.89
     houſe
    -0.88
     pleaſure
    -0.83
     purpoſe
    -0.83
     ſtand
    -0.82
     deſt
    -0.82
     poffible
    -0.81
    POSITIVE LOGITS
     with
    2.39
    with
    1.91
     WITH
    1.78
     With
    1.72
     avec
    1.66
    With
    1.64
     dengan
    1.59
     עם
    1.52
     với
    1.49
    WITH
    1.43
    Activations Density 0.410%

    No Known Activations