INDEX

Explanations

terms related to previous studies or historical context in research

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

preceding verbs in scientific literature

np_acts-logits-general · gemini-2.0-flash

previously identified research

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

tagext

-0.69

Alike

-0.56

 تعدى

-0.51

 voller

-0.50

★★★★★

-0.50

ImageContext

-0.49

ölkerung

-0.49

whose

-0.49

full

-0.49

AccessorTable

-0.48

POSITIVE LOGITS

fromnode

0.71

Vidite

0.65

 mentioned

0.62

 proposed

0.60

 afore

0.58

 által

0.58

 previously

0.57

 Paglinawan

0.57

 planned

0.56

 newly

0.56

Activations Density 0.362%

terms related to previous studies or historical context in research

preceding verbs in scientific literature

previously identified research

No Comments

No Known Activations