INDEX

Explanations

variables and concepts related to programming logic

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

Followed by French or Spanish words

np_acts-logits-general · gemini-2.0-flash

Spanish and French programming terms

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

-0.74

-0.61

-0.60

-0.58

-0.57

-0.56

-0.53

 žád

-0.53

 ninguno

-0.53

POSITIVE LOGITS

PreferredItem

0.96

 disambiguazione

0.95

Rüyada

0.94

 IMEI

0.93

])):

0.90

 initComponents

0.89

 createContext

0.86

 Catawiki

0.85

 propOrder

0.84

UserScript

0.83

Activations Density 0.080%

variables and concepts related to programming logic

Followed by French or Spanish words

Spanish and French programming terms

No Comments

No Known Activations