INDEX

Explanations

numerical values and references to measurements, data, or statistics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

numeric identifiers and references

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ſeinem

-0.85

 wiſſen

-0.82

 erſten

-0.82

 ſehr

-0.82

 geſch

-0.81

 فريبيس

-0.80

 geweſen

-0.80

 beſti

-0.80

ſſung

-0.79

<unused16>

-0.78

POSITIVE LOGITS

 altında

0.23

 específica

0.22

 varones

0.22

 jälkeen

0.22

 efectuar

0.22

ab

0.22

 selatan

0.21

0.20

pos

0.20

 liksom

0.20

Activations Density 0.120%

numerical values and references to measurements, data, or statistics

numeric identifiers and references

No Comments

No Known Activations