© 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. 4-GEMMASCOPE-RES-16K
    11. 4082
    Prev
    Next
    INDEX
    Explanations

    symbolic or graphical notations typically used in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -1.09
     Мексичка
    -0.84
     itſelf
    -0.79
    </tfoot>
    -0.78
     purpoſe
    -0.75
    neſs
    -0.75
    ContextHolder
    -0.73
     ―――――
    -0.73
    łgorzata
    -0.72
    otry
    -0.72
    POSITIVE LOGITS
    
    0.55
    redirected
    0.43
    inku
    0.43
    iked
    0.42
    serving
    0.41
    外の
    0.41
    uni
    0.41
    говор
    0.39
    missive
    0.38
    courtesy
    0.38
    Activations Density 0.239%

    No Known Activations