INDEX

Explanations

references to the JetBrains organization in programming contexts

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

jetbrains products

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 mulighed

-0.38

 fijo

-0.38

่ว

-0.35

providedIn

-0.35

 oculto

-0.35

diğinde

-0.34

 mulig

-0.34

Clik

-0.33

 steder

-0.32

 jossa

-0.30

POSITIVE LOGITS

jetbrains

2.45

intellij

1.02

Brains

0.82

AddTagHelper

0.74

 ReSharper

0.74

Sharper

0.71

 PhpStorm

0.69

printStackTrace

0.68

 BoxFit

0.68

RTSC

0.67

Activations Density 0.001%

references to the JetBrains organization in programming contexts

jetbrains products

No Comments

No Known Activations