INDEX

Explanations

first person pronouns, words describing states of being, and discussion of sleep disorders

oai_token-act-pair · gemini-2.0-flash

waking up

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 wake

-2.13

 wakes

-1.99

 woke

-1.91

 waking

-1.88

 Wake

-1.81

Wake

-1.78

 woken

-1.76

 awake

-1.70

wake

-1.70

 awoke

-1.64

POSITIVE LOGITS

 محفوظة

0.63

 <=",

0.62

InvalidProtocol

0.56

0.50

andExpect

0.50

fjspx

0.48

 parseFrom

0.47

wikidata

0.47

StructEnd

0.47

ToBounds

0.46

Activations Density 1.280%

first person pronouns, words describing states of being, and discussion of sleep disorders

waking up

No Comments

No Known Activations