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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6969
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "un-", indicating negation or the absence of a quality

    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
     épaules
    -0.47
     управління
    -0.39
     desemple
    -0.38
     satılık
    -0.37
     rých
    -0.37
     trône
    -0.37
     toiminta
    -0.36
     liitty
    -0.36
     antemano
    -0.36
    føring
    -0.36
    POSITIVE LOGITS
    un
    2.27
    UN
    1.28
    Un
    1.25
     Un
    1.20
    unz
    0.86
    unat
    0.85
    uns
    0.84
    unse
    0.84
    unna
    0.83
    unal
    0.81
    Activations Density 0.243%

    No Known Activations