© 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. 12240
    Prev
    Next
    INDEX
    Explanations

    references to seasonal events and activities related to transformation and renewal

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

    words and phrases related to preparation, readiness, and getting things done.

    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
     eens
    -0.32
     excru
    -0.30
    Cordialement
    -0.30
    てて
    -0.28
     agregado
    -0.28
    tilhar
    -0.27
    anskje
    -0.27
     kysy
    -0.27
    BagLayout
    -0.27
     monasterio
    -0.27
    POSITIVE LOGITS
     preparation
    3.27
     Preparation
    2.88
     preparations
    2.84
     preparing
    2.83
    preparation
    2.80
     prepare
    2.77
    Preparation
    2.64
     preparatory
    2.63
    prepar
    2.63
     prepares
    2.61
    Activations Density 0.747%

    No Known Activations