© 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. 8130
    Prev
    Next
    INDEX
    Explanations

    references to self-identity or the concept of "self"

    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
    彼此
    -0.58
     its
    -0.58
     they
    -0.57
    它們
    -0.56
    それぞれ
    -0.55
     eds
    -0.54
     collectively
    -0.54
     their
    -0.54
     internetowa
    -0.53
    它们
    -0.53
    POSITIVE LOGITS
     himself
    2.65
    himself
    2.33
     Himself
    1.95
     himſelf
    1.56
     herself
    1.49
    herself
    1.33
    他自己
    1.10
     sám
    1.04
     själv
    0.95
    sidemargin
    0.92
    Activations Density 0.091%

    No Known Activations