© 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. 15-GEMMASCOPE-RES-16K
    6. 13482
    Prev
    Next
    INDEX
    Explanations

    references to processes or methods that facilitate understanding or discovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     momente
    -0.45
    ́t
    -0.44
     Brim
    -0.42
    Lo
    -0.42
    strator
    -0.41
    all
    -0.40
    horn
    -0.40
     asuntos
    -0.39
    ̣
    -0.38
     مخطط
    -0.38
    POSITIVE LOGITS
     tramite
    1.05
     Through
    1.02
    verwijspagina
    1.01
    Through
    1.00
    THROUGH
    0.99
     través
    0.95
     via
    0.94
    Билгалдахарш
    0.93
     lenker
    0.93
     biais
    0.91
    Activations Density 0.157%

    No Known Activations