© 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. 35-GEMMASCOPE-RES-16K
    11. 9331
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal statements and testimonies in legal or administrative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    だよね
    -0.42
     Puoi
    -0.42
     puoi
    -0.42
    なんだけど
    -0.41
     verás
    -0.41
    だが
    -0.39
    だよ
    -0.38
     Puedes
    -0.37
     puedes
    -0.36
    cesz
    -0.36
    POSITIVE LOGITS
     Mr
    3.84
    Mr
    3.48
     Ms
    2.84
     Mrs
    2.69
     mr
    2.58
    Mrs
    2.39
    Ms
    2.33
     Messrs
    2.23
     آقای
    2.09
     Mister
    2.06
    Activations Density 1.097%

    No Known Activations