© 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. 2715
    Prev
    Next
    INDEX
    Explanations

    instances of the word "perfect" and its variants, indicating a focus on excellence or ideal conditions

    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
    Controllo
    -0.59
    dafrika
    -0.56
     wiser
    -0.56
     ancha
    -0.54
     efectivo
    -0.52
     gruesa
    -0.50
     NUKAT
    -0.50
     fortement
    -0.50
     igjen
    -0.49
    tubers
    -0.49
    POSITIVE LOGITS
     Perfect
    1.09
     perfect
    1.08
    Perfect
    1.07
     PERFECT
    1.06
     imperfect
    1.03
     imperfection
    1.02
    perfect
    1.01
    PERFECT
    1.00
     imperfections
    0.93
     IDEAL
    0.92
    Activations Density 0.046%

    No Known Activations