© 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. 27-GEMMASCOPE-RES-16K
    11. 11579
    Prev
    Next
    INDEX
    Explanations

    quantitative data and estimates related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorTagHelper
    -0.40
     utford
    -0.36
    有所
    -0.35
    AsUp
    -0.35
    siempre
    -0.33
    Abitanti
    -0.32
     Aussch
    -0.31
     Estaba
    -0.30
     Nachbarn
    -0.30
    LookAnd
    -0.30
    POSITIVE LOGITS
    一共
    0.74
     total
    0.68
    Approximately
    0.67
     approximately
    0.67
     totalt
    0.66
     총
    0.65
    共
    0.63
     Approximately
    0.63
     Altogether
    0.62
     Insgesamt
    0.61
    Activations Density 0.543%

    No Known Activations