© 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. 3-GEMMASCOPE-RES-16K
    11. 7835
    Prev
    Next
    INDEX
    Explanations

    instances of the word "a" and its variations, indicating a focus on indefinite articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -1.08
     nahilalakip
    -1.03
    MigrationBuilder
    -1.00
    rungsseite
    -0.89
    OGND
    -0.85
     disambiguazione
    -0.85
    IsMutable
    -0.84
     CreateTagHelper
    -0.82
     kasarigan
    -0.81
     propOrder
    -0.81
    POSITIVE LOGITS
     
    0.55
      
    0.45
    ↵↵
    0.44
    <eos>
    0.43
     [
    0.42
     (
    0.41
    ,
    0.40
     L
    0.39
     de
    0.39
    [
    0.39
    Activations Density 0.144%

    No Known Activations