© 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. 36-GEMMASCOPE-RES-16K
    11. 13048
    Prev
    Next
    INDEX
    Explanations

    references to ISBN numbers and links related to academic or literary resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kloped
    -0.49
    AndEndTag
    -0.49
     maxim
    -0.48
    intios
    -0.48
     FORT
    -0.48
    </tfoot>
    -0.48
     maxi
    -0.48
     дописавши
    -0.48
     MainAxisSize
    -0.47
    tend
    -0.47
    POSITIVE LOGITS
     ISBN
    0.66
    ISBN
    0.60
     isbn
    0.57
    isbn
    0.48
     sienten
    0.37
     impreso
    0.34
    setContentView
    0.34
    setDo
    0.33
     книге
    0.33
    TokenNameLPAREN
    0.32
    Activations Density 0.286%

    No Known Activations