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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 16065
    Prev
    Next
    INDEX
    Explanations

    syntactic structures related to programming and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.32
     itemprop
    -0.27
    protoimpl
    -0.24
     demurrer
    -0.24
    bouncycastle
    -0.22
     millón
    -0.22
     alfombra
    -0.22
    日閲覧
    -0.22
    🤞
    -0.22
     gouver
    -0.21
    POSITIVE LOGITS
    uxxxx
    0.83
    rungsseite
    0.77
     kaarangay
    0.76
    Personendaten
    0.76
     betweenstory
    0.75
     Италијани
    0.75
     ویکی‌پدی
    0.75
     Numerade
    0.67
    StoryboardSegue
    0.65
    Personensuche
    0.65
    Activations Density 1.315%

    No Known Activations