© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-GEMMASCOPE-RES-16K
    11. 2958
    Prev
    Next
    INDEX
    Explanations

    sections of code or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -1.92
    ,
    -1.43
    -
    -1.42
     
    -1.41
     (
    -1.34
    :
    -1.34
     -
    -1.32
     "
    -1.27
     and
    -1.23
     .
    -1.16
    POSITIVE LOGITS
     indígen
    1.45
     Wikiseite
    1.40
     mijne
    1.34
     queſta
    1.33
     increí
    1.33
     miniaturka
    1.31
     desmotivaciones
    1.29
    "])
    1.28
     Grüsse
    1.28
     Italij
    1.28
    Activations Density 0.937%

    No Known Activations