© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2317
    Prev
    Next
    INDEX
    Explanations

    concepts related to restoration and recovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.72
     autorytatywna
    -0.70
     Himo
    -0.70
    Obrázky
    -0.68
    BufferException
    -0.67
     Winaray
    -0.67
    RenderAtEndOf
    -0.64
    ыгана
    -0.63
     Wiktionnaire
    -0.63
    orsese
    -0.61
    POSITIVE LOGITS
     lost
    1.40
    lost
    1.22
     Lost
    1.09
    Lost
    1.05
     damaged
    1.02
     LOST
    1.00
     forgotten
    0.99
     Damaged
    0.94
    LOST
    0.90
    damaged
    0.88
    Activations Density 0.159%

    No Known Activations