© 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. 14043
    Prev
    Next
    INDEX
    Explanations

    expressions of self-identity and emotional states

    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
     conmigo
    -1.16
     comigo
    -1.02
     nous
    -0.96
     us
    -0.86
     conosco
    -0.82
     нам
    -0.81
     meille
    -0.81
     nás
    -0.80
     me
    -0.80
     لنا
    -0.79
    POSITIVE LOGITS
     myself
    2.32
    myself
    1.67
     myſelf
    1.44
     Myself
    1.33
     خودم
    0.97
    AnchorStyles
    0.97
    我自己
    0.88
     говорю
    0.87
     personally
    0.85
     हूं
    0.84
    Activations Density 0.823%

    No Known Activations