© 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. 25-GEMMASCOPE-RES-16K
    6. 6600
    Prev
    Next
    INDEX
    Explanations

    punctuation and syntactic structures in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    הערות
    -0.48
    The
    -0.45
    তথ্যসূত্র
    -0.43
     odds
    -0.43
    Instead
    -0.43
    criptures
    -0.42
     Зачем
    -0.42
    Usually
    -0.42
    etheless
    -0.42
     Почему
    -0.41
    POSITIVE LOGITS
    enumi
    0.67
    FieldBuilder
    0.66
    UMBIA
    0.55
    NameInMap
    0.54
    SuspendLayout
    0.54
    numerusform
    0.53
    .*;
    
    0.52
    IInterface
    0.52
     unknownFields
    0.52
     ProtoMessage
    0.50
    Activations Density 0.070%

    No Known Activations