INDEX

Explanations

place names and geographic references

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

place names followed by punctuation

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

fjspx

-0.40

ússia

-0.35

phere

-0.34

⊝

-0.34

tagPool

-0.34

ạy

-0.33

 Италијани

-0.33

OpenHelper

-0.33

 Aérea

-0.33

 będą

-0.32

POSITIVE LOGITS

tagHelperRunner

0.58

AutoModerator

0.57

 ModelExpression

0.53

atown

0.52

henge

0.52

 linkovi

0.51

Efq

0.50

Geplaatst

0.50

 للاسماء

0.50

期刊论文

0.49

Activations Density 0.249%

place names and geographic references

place names followed by punctuation

No Comments

No Known Activations

place names and geographic references

place names followed by punctuation

No Comments

No Known Activations