© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 2295
    Prev
    Next
    INDEX
    Explanations

    mathematical notation related to limits or convergence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.75
     JAXBElement
    -0.73
     queſta
    -0.73
    ="@+
    -0.71
    migrationBuilder
    -0.71
    曖昧さ回避
    -0.70
    providedIn
    -0.69
    EndContext
    -0.69
    Билгалдахарш
    -0.69
     IBOutlet
    -0.68
    POSITIVE LOGITS
     J
    0.35
     L
    0.35
     G
    0.35
     P
    0.35
     K
    0.35
     F
    0.34
     p
    0.34
     D
    0.33
     g
    0.33
     S
    0.32
    Activations Density 5.196%

    No Known Activations