INDEX

Explanations

references to regions in a coding or programming context

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

Code, dates, and math symbols

np_acts-logits-general · gemini-2.0-flash

code related syntax

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

</em>

-1.04

</u>

-0.90

</h5>

-0.82

</i>

-0.73

GeoNames

-0.67

*/

-0.65

straints

-0.58

”;

-0.55

‚

-0.55

Javadoc

-0.54

POSITIVE LOGITS

 CreateTagHelper

1.15

WireFormatLite

0.91

tagHelperRunner

0.80

=$?

0.77

')")

0.75

expandindo

0.75

)))),

0.72

']")

0.72

 propOrder

0.68

mybatisplus

0.68

Activations Density 0.543%

references to regions in a coding or programming context

Code, dates, and math symbols

code related syntax

No Comments

No Known Activations