© 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. 2-GEMMASCOPE-RES-16K
    11. 9015
    Prev
    Next
    INDEX
    Explanations

    terms related to retention and holding onto things or positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.79
    extAlignment
    -0.69
    
    -0.68
    россий
    -0.60
    prüche
    -0.60
    dud
    -0.59
    hup
    -0.58
     acorns
    -0.56
     idols
    -0.56
     yi
    -0.55
    POSITIVE LOGITS
    retain
    0.84
     retention
    0.83
     Retention
    0.81
     retain
    0.81
     retained
    0.76
    retention
    0.73
     Placement
    0.72
     placement
    0.71
     Paglinawan
    0.69
    Retention
    0.68
    Activations Density 0.102%

    No Known Activations