INDEX

Explanations

repeated occurrences of specific articles, symbols, and references to mathematical concepts

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

Appears before specific nouns

np_acts-logits-general · gemini-2.0-flash

technical terms following "the"

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

verwijspagina

-0.53

zzleHttp

-0.52

MemoryWarning

-0.51

piram

-0.50

Hochspringen

-0.49

AccessorTable

-0.49

 XCTest

-0.48

FieldBuilder

-0.48

windowFixed

-0.47

parsedMessage

-0.47

POSITIVE LOGITS

 Investigaciones

0.45

 this

0.45

 these

0.45

 their

0.43

 Metropolitana

0.43

 aceste

0.42

 actuel

0.42

 existing

0.41

 estos

0.40

 nocturna

0.40

Activations Density 1.395%

repeated occurrences of specific articles, symbols, and references to mathematical concepts

Appears before specific nouns

technical terms following "the"

No Comments

No Known Activations