INDEX

Explanations

elements related to software dependencies and configurations

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

Code-related terms and symbols

np_acts-logits-general · gemini-2.0-flash

code syntax and configuration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MemoryWarning

-0.81

AddTagHelper

-0.71

Демографія

-0.64

principalTable

-0.63

kloped

-0.62

 Biôgrafia

-0.61

 ویکی‌پدی

-0.61

Jereo

-0.58

interopRequire

-0.58

 defaultstate

-0.58

POSITIVE LOGITS

 InputDecoration

0.56

ⓘ

0.52

SupportActionBar

0.51

 rumen

0.48

ciers

0.47

gitter

0.47

Ufficio

0.47

 Catt

0.46

cycline

0.45

 trending

0.45

Activations Density 0.081%

elements related to software dependencies and configurations

Code-related terms and symbols

code syntax and configuration

No Comments

No Known Activations