© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10061
    Prev
    Next
    INDEX
    Explanations

    function declarations and their corresponding closing braces in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    なんと
    -0.49
     Koss
    -0.48
    ceira
    -0.44
    ichio
    -0.44
    -0.43
    *
    -0.43
    trische
    -0.43
     TO
    -0.42
    ட்ச
    -0.42
    datatype
    -0.42
    POSITIVE LOGITS
     مشين
    1.04
    ArgsConstructor
    0.84
    SourceChecksum
    0.82
     MainAxisSize
    0.81
    adaptiveStyles
    0.81
    OGND
    0.80
    +#+#
    0.79
    تقاوى
    0.76
    addContainerGap
    0.74
    AndEndTag
    0.74
    Activations Density 0.174%

    No Known Activations