© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 2161
    Prev
    Next
    INDEX
    Explanations

    patterns and structures associated with programming concepts, particularly around variables and iteration in 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
     Monfieur
    -0.92
     myſelf
    -0.87
     Cæsar
    -0.84
     Efq
    -0.80
     Jefus
    -0.79
     Majefty
    -0.78
     Theſe
    -0.78
     himſelf
    -0.77
     ſeveral
    -0.77
     Diſ
    -0.72
    POSITIVE LOGITS
     Italijanski
    0.53
    enumi
    0.47
     saites
    0.46
    Personendaten
    0.43
    GeoNames
    0.43
    __(/*!
    0.43
     frase
    0.42
    WriteTagHelper
    0.42
     opción
    0.42
     combinación
    0.42
    Activations Density 0.016%

    No Known Activations