INDEX

Explanations

structures and symbols used in programming and data representation

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

Code or mathematical notation

np_acts-logits-general · gemini-2.0-flash

code formatting or timestamps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 Савезне

-0.65

}(\

-0.64

yled

-0.63

Portály

-0.60

tiérrez

-0.60

 كومونز

-0.60

ilibre

-0.60

rzost

-0.59

hematical

-0.56

ValueGeneration

-0.55

POSITIVE LOGITS

↵

1.93

↵↵

1.08

0.94

↵↵↵

0.75

</h2>

0.71

</h3>

0.71

</h4>

0.69

</h1>

0.66

__":

0.61

])),

0.60

Activations Density 0.608%

structures and symbols used in programming and data representation

Code or mathematical notation

code formatting or timestamps

No Comments

No Known Activations