© 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. 16-GEMMASCOPE-RES-16K
    11. 13358
    Prev
    Next
    INDEX
    Explanations

    Java programming language elements related to file handling and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code and numerical identifiers

    np_acts-logits-general · gemini-2.0-flash

    View, Point, 3, 9

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     western
    -0.51
     real
    -0.50
    tigma
    -0.49
    indari
    -0.48
    ideos
    -0.48
    idere
    -0.48
     án
    -0.48
    iforn
    -0.48
     Western
    -0.47
     ne
    -0.47
    POSITIVE LOGITS
     disambiguazione
    0.92
     متعلقه
    0.87
     ujednoznacz
    0.78
     فريبيس
    0.70
    Xna
    0.69
    UserScript
    0.66
     snippetHide
    0.66
    verwijspagina
    0.65
     Walkover
    0.64
    stdc
    0.64
    Activations Density 0.032%

    No Known Activations