INDEX

Explanations

references to statistical values or metrics used in data analysis

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

Difference or times

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

 Paglinawan

-0.86

 queſta

-0.74

rungsseite

-0.73

 zijne

-0.73

sizeCache

-0.71

səhifə

-0.71

AsUp

-0.70

 Italijanski

-0.69

ConstraintMaker

-0.69

 Wikiseite

-0.68

POSITIVE LOGITS

The

0.40

0.38

0.36

0.35

“

0.35

Activations Density 0.000%

references to statistical values or metrics used in data analysis

Difference or times

No Comments

No Known Activations