INDEX

Explanations

expressions of doubt or uncertainty

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

isn't really

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Inscrivez

-0.59

ViewImports

-0.52

 avoient

-0.47

 pouvoit

-0.47

fromCharCode

-0.43

 étoit

-0.43

GIVEREF

-0.42

PathVariable

-0.42

 múltiple

-0.42

 HasFactory

-0.42

POSITIVE LOGITS

lında

0.60

really

0.60

Really

0.59

 really

0.57

不太

0.56

 layui

0.55

 Really

0.55

pretty

0.55

 Hardly

0.52

 egentlig

0.51

Activations Density 0.016%

expressions of doubt or uncertainty

isn't really

No Comments

No Known Activations