INDEX

Explanations

references to formatted textual content, particularly in coding or mathematical contexts

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

Mathematical or programming-related text fragments

np_acts-logits-general · gemini-2.0-flash

configuration, permissions, or legal agency

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

ScopeManager

-0.65

contentLoaded

-0.63

Jereo

-0.62

 marchés

-0.59

 Meksiku

-0.58

VertexAttrib

-0.58

 Emits

-0.55

 szem

-0.53

 يتيمه

-0.53

Tazama

-0.53

POSITIVE LOGITS

awtextra

0.56

0.55

Kou

0.49

icose

0.49

initComponents

0.48

ก่

0.48

ารถ

0.47

ագրություններ

0.47

ροι

0.46

ruptedException

0.45

Activations Density 0.066%

references to formatted textual content, particularly in coding or mathematical contexts

Mathematical or programming-related text fragments

configuration, permissions, or legal agency

No Comments

No Known Activations

references to formatted textual content, particularly in coding or mathematical contexts

Mathematical or programming-related text fragments

configuration, permissions, or legal agency

No Comments

No Known Activations