INDEX

Explanations

non-English characters and symbols

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

Non-English characters and symbols

np_acts-logits-general · gemini-2.0-flash

programming terms, code snippets, and technical identifiers

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 enfans

-0.49

 Juifs

-0.45

vänd

-0.41

 pouvoit

-0.41

 feroit

-0.40

 noiva

-0.39

 auroit

-0.39

 Grecs

-0.38

Fordítás

-0.38

 poète

-0.38

POSITIVE LOGITS

tagHelperRunner

0.69

BibitemShut

0.67

twimg

0.58

MemoryWarning

0.58

 betweenstory

0.56

AddTagHelper

0.55

parsedMessage

0.53

RegressionTest

0.53

ViewFeatures

0.52

jspx

0.52

Activations Density 0.239%

non-English characters and symbols

Non-English characters and symbols

programming terms, code snippets, and technical identifiers

No Comments

No Known Activations