© 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. 5-GEMMASCOPE-RES-16K
    11. 2969
    Prev
    Next
    INDEX
    Explanations

    code elements related to data structures, specifically strings and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -0.68
    featureID
    -0.65
    addContainerGap
    -0.60
    IsContent
    -0.58
    __))
    -0.56
     MenuView
    -0.55
    expandindo
    -0.55
     trams
    -0.55
    ")));
    -0.55
    
    -0.55
    POSITIVE LOGITS
    Personensuche
    0.60
    +#+#
    0.57
     ContentValues
    0.57
    ::__
    0.56
    ivasan
    0.55
    rétaire
    0.48
     Bewegung
    0.47
    TreeMap
    0.46
    География
    0.46
    paramMap
    0.45
    Activations Density 0.135%

    No Known Activations