© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 2836
    Prev
    Next
    INDEX
    Explanations

    instances of the word "flat" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -1.09
     CreateTagHelper
    -1.08
    PMailer
    -1.05
     StringTokenizer
    -1.05
    PhysRev
    -0.99
    ---*/
    -0.96
    usercontent
    -0.92
    Personensuche
    -0.92
    CodedInputStream
    -0.90
    __':
    
    -0.90
    POSITIVE LOGITS
     flat
    1.80
     Flat
    1.74
    flat
    1.67
    Flat
    1.61
     FLAT
    1.61
    FLAT
    1.53
     flats
    1.50
     Flats
    1.38
    flats
    1.26
    FlatList
    1.25
    Activations Density 0.026%

    No Known Activations