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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4702
    Prev
    Next
    INDEX
    Explanations

    instances of the word "perfect" and its collocations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "perfect"

    np_acts-logits-general · gemini-2.0-flash

    perfect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gruesa
    -0.45
     fortement
    -0.42
     znacznie
    -0.41
     mocno
    -0.41
     fuertemente
    -0.40
     köpek
    -0.40
     hodně
    -0.38
     Jungen
    -0.38
    chehen
    -0.37
     drogas
    -0.37
    POSITIVE LOGITS
    perfect
    1.19
     perfect
    1.19
    Perfect
    1.13
     PERFECT
    1.13
     Perfect
    1.12
    PERFECT
    1.07
    perfectly
    1.02
     perfectly
    0.98
     Perfectly
    0.97
     perfetta
    0.92
    Activations Density 0.141%

    No Known Activations