© 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. 15-GEMMASCOPE-RES-16K
    11. 4603
    Prev
    Next
    INDEX
    Explanations

    special characters or formatting indicators in code documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -1.02
     ब्रेकडाउन
    -0.91
    OGND
    -0.89
     betweenstory
    -0.85
    pushFollow
    -0.84
    出版年
    -0.84
     Paglinawan
    -0.84
    
    -0.81
    findpost
    -0.81
     queſta
    -0.80
    POSITIVE LOGITS
    //
    0.63
    ///
    0.56
     *
    0.49
    *
    0.48
    /*
    0.47
    #
    0.47
    [toxicity=0]
    0.46
    I
    0.46
    _
    0.46
    0
    0.44
    Activations Density 0.125%

    No Known Activations