INDEX

Explanations

references to immune system processes and cytokine activity

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

Inflammatory processes involving macrophages

np_acts-logits-general · gemini-2.0-flash

macrophages and inflammation

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

 AppColors

-0.49

 typelib

-0.48

rungsseite

-0.47

 Bress

-0.47

 Rücks

-0.47

 Dür

-0.47

 Fools

-0.46

 Samson

-0.46

glTexCoord

-0.46

 fools

-0.44

POSITIVE LOGITS

 inflammatory

1.29

 inflammation

1.23

 Inflammatory

1.17

lammatory

1.16

 Inflammation

1.15

inflammatory

1.12

inflammation

1.08

Infla

1.06

 infla

1.04

infla

0.99

Activations Density 1.725%

references to immune system processes and cytokine activity

Inflammatory processes involving macrophages

macrophages and inflammation

No Comments

No Known Activations