© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8274
    Prev
    Next
    INDEX
    Explanations

    elements related to function definitions and annotations 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 @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.55
    transQ
    -0.54
     Hence
    -0.48
    السكان
    -0.45
    PushButton
    -0.45
    hence
    -0.45
    AutoScale
    -0.44
    FlowLayout
    -0.44
     useAuth
    -0.44
     useAppContext
    -0.43
    POSITIVE LOGITS
    ValueStyle
    0.54
     Chwiliwch
    0.53
    parametrize
    0.43
    mazioni
    0.40
     pazienti
    0.40
     обору
    0.38
    umber
    0.37
    ISupport
    0.37
     незавершена
    0.37
     rå
    0.36
    Activations Density 0.188%

    No Known Activations