© 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. 1339
    Prev
    Next
    INDEX
    Explanations

    programming actions and methods related to session management

    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
    beste
    -0.59
    ECONDS
    -0.55
    DAQ
    -0.54
     Ass
    -0.51
    jenih
    -0.51
    asson
    -0.50
    lement
    -0.50
    ongi
    -0.50
     Group
    -0.50
    ever
    -0.49
    POSITIVE LOGITS
    ConstraintMaker
    0.72
     beginnetje
    0.67
     Extragalactic
    0.63
     chi̍t
    0.59
    mergeFrom
    0.58
     wireType
    0.58
     CreateTagHelper
    0.57
     him
    0.56
    bcryptjs
    0.56
     membuatnya
    0.55
    Activations Density 0.156%

    No Known Activations