© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9876
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to input and output in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BorderFactory
    -0.47
    stateProvider
    -0.43
    ever
    -0.42
    AxisAlignment
    -0.41
    eyes
    -0.40
     auftreten
    -0.40
    e
    -0.39
    rand
    -0.38
    over
    -0.37
     Zeller
    -0.37
    POSITIVE LOGITS
     getInput
    0.83
     input
    0.82
     Input
    0.79
    setInput
    0.75
     INPUT
    0.75
    input
    0.72
    inputData
    0.69
    Input
    0.69
    RenderAtEndOf
    0.68
    INPUT
    0.65
    Activations Density 0.175%

    No Known Activations