INDEX

Explanations

phrases indicating knowledge or claims about previous studies

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

"[this] is the first"

np_acts-logits-general · gemini-2.0-flash

first time reporting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

UrlResolution

-0.73

SpringBootTest

-0.72

LabelTagHelper

-0.61

WebVitals

-0.59

 PackageManager

-0.55

libft

-0.54

::::::::

-0.54

IonicModule

-0.53

RegressionTest

-0.51

 AssemblyCulture

-0.51

POSITIVE LOGITS

 самым

0.72

 самое

0.69

 самы

0.69

 самый

0.68

Javadoc

0.66

 самая

0.65

是最

0.64

cea

0.63

唯一

0.61

 가장

0.59

Activations Density 0.492%

phrases indicating knowledge or claims about previous studies

"[this] is the first"

first time reporting

No Comments

No Known Activations