© 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. 33-GEMMASCOPE-RES-16K
    11. 2197
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation and unique formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     penghar
    -0.35
     Grüßen
    -0.35
     abandonado
    -0.34
     Gonçalves
    -0.34
     vocación
    -0.33
     Polsek
    -0.33
     península
    -0.33
     aislado
    -0.32
     desaparición
    -0.31
     damska
    -0.31
    POSITIVE LOGITS
     CreateTagHelper
    1.09
    rungsseite
    0.84
    <unused14>
    0.80
    <unused52>
    0.80
     disambiguazione
    0.80
    <unused68>
    0.79
    <unused79>
    0.79
    [@BOS@]
    0.79
    <unused8>
    0.79
    <unused16>
    0.79
    Activations Density 0.356%

    No Known Activations