© 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. 31-GEMMASCOPE-RES-16K
    11. 15063
    Prev
    Next
    INDEX
    Explanations

    names of classical music compositions and their performers

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

    opera titles and composer names in biographical and discographical contexts.

    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
    arnia
    -0.38
    %&
    -0.32
    blatt
    -0.32
    degard
    -0.31
    RUPT
    -0.31
     wahre
    -0.31
     неба
    -0.31
    abo
    -0.31
     Hollywood
    -0.30
    avant
    -0.30
    POSITIVE LOGITS
     iſt
    0.71
     ſind
    0.68
     Monfieur
    0.68
     queſta
    0.65
     cherchés
    0.63
     auffi
    0.63
     мәкал
    0.60
    makeConstraints
    0.60
     ſol
    0.59
    WriteTagHelper
    0.59
    Activations Density 0.171%

    No Known Activations