INDEX

Explanations

references to geographical locations and landmarks

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

mountains mountains hiking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

SourceChecksum

-0.54

]=>

-0.47

 Paglinawan

-0.47

 iconTwitter

-0.46

getDoctrine

-0.43

PageState

-0.41

ArgsConstructor

-0.40

Brainz

-0.39

brick

-0.39

 betweenstory

-0.39

POSITIVE LOGITS

 hiking

0.55

 summit

0.53

summit

0.48

 hike

0.48

 Hiking

0.46

登山

0.46

 Gipfel

0.45

riezmann

0.45

Summit

0.44

 hiked

0.44

Activations Density 0.106%

references to geographical locations and landmarks

mountains mountains hiking

No Comments

No Known Activations