© 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. 2-GEMMASCOPE-RES-16K
    11. 15286
    Prev
    Next
    INDEX
    Explanations

    terms related to loss or defeat

    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
     loose
    -0.92
    loose
    -0.80
    Loose
    -0.80
     Loose
    -0.72
     esque
    -0.70
    LEncoder
    -0.68
    ureka
    -0.67
    SKE
    -0.64
    ✨:
    -0.62
     esquecer
    -0.61
    POSITIVE LOGITS
     loss
    2.64
     Loss
    2.42
    Loss
    2.28
    loss
    2.21
     LOSS
    2.16
    LOSS
    1.91
     losses
    1.79
     Losses
    1.59
     Verlust
    1.56
     perte
    1.53
    Activations Density 0.163%

    No Known Activations