© 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. 10777
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and concepts

    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
    CppMethod
    -0.39
    UnusedPrivate
    -0.39
     MainAxisSize
    -0.38
    AxisAlignment
    -0.36
    HasForeignKey
    -0.35
     Мексичка
    -0.32
    ExtendWith
    -0.31
     continúas
    -0.30
     bague
    -0.30
     отредактировал
    -0.30
    POSITIVE LOGITS
     submissions
    0.75
     autorytatywna
    0.70
     submission
    0.69
     Submission
    0.68
     Submissions
    0.66
     Contest
    0.64
     Problem
    0.62
     SUBMIT
    0.60
    contest
    0.60
     problem
    0.59
    Activations Density 0.447%

    No Known Activations