© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15294
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and syntax elements in a programming context

    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
     canteen
    -0.47
    MutableLiveData
    -0.46
     ویکی‌پدی
    -0.45
    NGC
    -0.44
     Añade
    -0.44
    giphy
    -0.44
    */),
    -0.43
    Phaser
    -0.43
     gyhoeddwyd
    -0.43
     maine
    -0.43
    POSITIVE LOGITS
    hpp
    0.61
    UnsafeEnabled
    0.57
    PerformLayout
    0.55
     يتيمه
    0.49
    h
    0.43
     للمعارف
    0.43
    simpleType
    0.39
    culable
    0.38
    cito
    0.36
    eseorang
    0.36
    Activations Density 0.188%

    No Known Activations