© 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. 7189
    Prev
    Next
    INDEX
    Explanations

    references to books or articles

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

    the beginning of sentences or clauses, particularly emphasizing the subject "This" or "We".

    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
    ge
    -0.29
     incluido
    -0.29
     arah
    -0.29
    ",@"
    -0.27
     navideñas
    -0.27
     cuentos
    -0.26
     incluida
    -0.26
     incluidos
    -0.25
     afectado
    -0.25
     понравилось
    -0.25
    POSITIVE LOGITS
     wikipagina
    1.32
    verwijspagina
    1.03
     resourceCulture
    1.02
     Wikiseite
    0.95
     <<<<<<<<<<<<<<
    0.90
    findpost
    0.89
    LikeLiked
    0.83
     surla
    0.80
    Aiheesta
    0.79
     Audiodateien
    0.79
    Activations Density 2.340%

    No Known Activations