INDEX

Explanations

specific scientific terms and concepts, particularly in relation to biological processes

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

Code or math symbols

np_acts-logits-general · gemini-2.0-flash

Provincial Key TIP

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

}{*}{

-0.63

 صوتيه

-0.61

DBNull

-0.53

ArgsConstructor

-0.52

بوابة

-0.52

adze

-0.50

جوايز

-0.49

 defStyleAttr

-0.49

 bParam

-0.48

ESTON

-0.48

POSITIVE LOGITS

AnchorTagHelper

0.66

 AssemblyProduct

0.64

WireFormatLite

0.59

RenderAtEndOf

0.55

SharedCtor

0.54

 Guardia

0.51

spesies

0.50

 Sandler

0.49

깥

0.48

 Upan

0.47

Activations Density 0.132%

specific scientific terms and concepts, particularly in relation to biological processes

Code or math symbols

Provincial Key TIP

No Comments

No Known Activations