© 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. 12-GEMMASCOPE-RES-16K
    6. 14375
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals in governmental, educational, and professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    неопр
    -0.51
     AssemblyCulture
    -0.46
    NSNotification
    -0.43
    Redaktion
    -0.43
    miştir
    -0.43
    ValueGeneration
    -0.42
    CGRectMake
    -0.41
    tableFuture
    -0.40
    ">'.$
    -0.39
    RTRS
    -0.39
    POSITIVE LOGITS
     &___
    0.90
    RegistryLite
    0.74
    ---*/
    0.68
    省市镇
    0.67
     ſche
    0.65
    --)
    
    0.64
     lccn
    0.64
    Personendaten
    0.63
     Deputy
    0.63
    Numerology
    0.63
    Activations Density 0.244%

    No Known Activations