© 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. 465
    Prev
    Next
    INDEX
    Explanations

    terms related to inventions and devices

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

    technical terms related to mechanisms and functions

    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
     ujednoznacz
    -0.60
     Thoma
    -0.59
    verwijspagina
    -0.56
    Билгалдахарш
    -0.54
    multirow
    -0.54
     FetchType
    -0.52
     apă
    -0.52
    HomeAsUpEnabled
    -0.51
    
    -0.51
     <",
    -0.50
    POSITIVE LOGITS
     turntable
    1.07
     record
    1.04
     Record
    1.01
    Record
    0.94
     records
    0.93
    record
    0.93
     stylus
    0.92
     RECORD
    0.92
     Records
    0.88
    Records
    0.86
    Activations Density 0.241%

    No Known Activations