© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 8620
    Prev
    Next
    INDEX
    Explanations

    structure definitions and export symbols in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.40
     actual
    -0.30
     actually
    -0.29
     "..\..\..\
    -0.29
    OleDb
    -0.29
    #
    -0.28
     αὐ
    -0.28
     шаг
    -0.28
     ocur
    -0.28
     doll
    -0.27
    POSITIVE LOGITS
    printk
    0.62
    TestingModule
    0.60
    tinyos
    0.57
    MultipartFile
    0.54
    CharField
    0.54
     zapo
    0.52
    endcsname
    0.52
    ::_('
    0.52
    unsplash
    0.52
    complexContent
    0.52
    Activations Density 0.867%

    No Known Activations