INDEX

Explanations

deep

np_max-act-logits · gemini-2.0-flash

the word "deep" and closely related concepts like "shallow" and "depth," sometimes in a metaphorical sense.

oai_token-act-pair · gemini-2.0-flash

deep

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ImageContext

-0.65

 виправивши

-0.61

loài

-0.60

expandindo

-0.59

ItemBackground

-0.57

یرات

-0.57

Datuak

-0.53

RectangleBorder

-0.52

InputBorder

-0.50

aş

-0.49

POSITIVE LOGITS

 Deep

0.73

Deep

0.73

 deep

0.73

deep

0.72

 deepest

0.69

浅

0.66

 DEEP

0.65

 deeper

0.65

 shallow

0.65

 глубо

0.63

Activations Density 1.126%

deep

the word "deep" and closely related concepts like "shallow" and "depth," sometimes in a metaphorical sense.

deep

No Comments

No Known Activations