© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 11620
    Prev
    Next
    INDEX
    Explanations

    punctuation marks used to denote the ends of statements or emotional expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wählen
    -0.25
    ...
    -0.25
    initial
    -0.24
    jan
    -0.24
    Lol
    -0.24
    bindung
    -0.23
    Jan
    -0.22
    u
    -0.22
    lo
    -0.22
    さ
    -0.22
    POSITIVE LOGITS
    httphttps
    1.04
    parsedMessage
    0.96
     للاسماء
    0.90
    ſelf
    0.88
    lapsingToolbar
    0.86
    RegressionTest
    0.85
    elemField
    0.82
     Houſe
    0.81
     ſei
    0.80
    Rhestr
    0.79
    Activations Density 0.129%

    No Known Activations