INDEX

Explanations

text related to the creation or instantiation of objects and data structures

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

created by or on

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 near

-0.47

 arşivlendi

-0.44

 others

-0.43

 ✭✭

-0.41

 respect

-0.40

 otherwise

-0.40

 dramatic

-0.39

 southern

-0.38

 comparative

-0.38

 sitten

-0.38

POSITIVE LOGITS

Datuak

0.84

Created

0.82

Erstellt

0.73

 nahilalakip

0.65

AutoScaleMode

0.64

Hentet

0.64

 AssemblyTitle

0.61

 للاسماء

0.60

GEBURTSDATUM

0.57

created

0.56

Activations Density 0.000%

text related to the creation or instantiation of objects and data structures

created by or on

No Comments

No Known Activations