INDEX

Explanations

the presence of various medical and health-related measurements or attributes

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

Text formatting and data tables

np_acts-logits-general · gemini-2.0-flash

variable names and code constructs

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 desmotivaciones

-0.93

ſcher

-0.90



-0.85

səhifə

-0.84

 queſta

-0.84

bootstrapcdn

-0.81

 jadx

-0.80

 auffi

-0.78

 SwitchCompat

-0.77

 feroit

-0.77

POSITIVE LOGITS

1.15

0.92

0.82

0.80

0.78

0.77

0.68

0.67

Activations Density 0.368%

the presence of various medical and health-related measurements or attributes

Text formatting and data tables

variable names and code constructs

No Comments

No Known Activations