© 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. 591
    Prev
    Next
    INDEX
    Explanations

    terms related to recovery, rehabilitation, or reclaiming lost abilities

    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
     Вікі
    -0.75
    SequentialGroup
    -0.73
    BufferException
    -0.71
     الرياضيه
    -0.65
     beginnetje
    -0.63
     propOrder
    -0.62
    aziland
    -0.62
     Numerade
    -0.59
    anskrit
    -0.59
    presso
    -0.58
    POSITIVE LOGITS
     recover
    2.46
     recovered
    2.28
     recovering
    2.26
     recovers
    2.21
     recovery
    2.17
     Recover
    2.05
    recover
    1.98
    Recover
    1.96
    recovered
    1.89
     Recovery
    1.85
    Activations Density 0.098%

    No Known Activations