© 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. 20-GEMMASCOPE-RES-16K
    11. 4320
    Prev
    Next
    INDEX
    Explanations

    phrases related to the creation or formation of objects or concepts

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

    technical or mathematical language involving processes of creation, formation, or constructing.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.39
    because
    -0.35
     gim
    -0.35
     because
    -0.35
     due
    -0.34
     Lal
    -0.33
     debido
    -0.33
     seien
    -0.32
    /*++
    -0.32
     etc
    -0.32
    POSITIVE LOGITS
     MainAxisSize
    0.86
     EconPapers
    0.81
    IntoConstraints
    0.77
     مشين
    0.72
    bootstrapcdn
    0.68
     BoxFit
    0.64
    parsedMessage
    0.64
    createComponent
    0.63
    providedIn
    0.63
    AccessorTable
    0.63
    Activations Density 0.362%

    No Known Activations