© 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. 31-GEMMASCOPE-RES-16K
    11. 12295
    Prev
    Next
    INDEX
    Explanations

    references to scientific proceedings and research outputs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    academic paper citations and reference formatting.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.51
     pleaſure
    -0.50
     ſche
    -0.50
     itſelf
    -0.48
     purpoſe
    -0.48
    IndentedString
    -0.46
    MergeFrom
    -0.46
     Majefty
    -0.46
     autorytatywna
    -0.46
    parency
    -0.46
    POSITIVE LOGITS
     conference
    1.16
     Conference
    1.12
    Conference
    1.03
     poster
    0.94
    conference
    0.92
     CONFERENCE
    0.90
     Abstracts
    0.89
     Posters
    0.86
     Poster
    0.85
    Poster
    0.83
    Activations Density 0.352%

    No Known Activations