© 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. 14-GEMMASCOPE-RES-16K
    6. 9866
    Prev
    Next
    INDEX
    Explanations

    various data types and their classifications within a structured dataset

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Domínguez
    -0.44
    opencv
    -0.43
    wür
    -0.43
    UTELY
    -0.43
    prech
    -0.42
    стюм
    -0.42
     McKenna
    -0.42
    bral
    -0.40
     occur
    -0.39
     superficial
    -0.39
    POSITIVE LOGITS
     متعلقه
    1.10
    تقاوى
    1.07
     betweenstory
    0.90
    tagHelperRunner
    0.90
     pinulongan
    0.88
    StructEnd
    0.87
     lenker
    0.87
     AssemblyCulture
    0.84
    ExtendWith
    0.84
    resizingMask
    0.84
    Activations Density 0.348%

    No Known Activations