INDEX

Explanations

occurrences of specific programming language syntax or structural elements

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

special characters or punctuation

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

tagHelperRunner

-1.03

AddTagHelper

-1.00

 Infórmanos

-0.97

OGND

-0.87

GOTREF

-0.85

WriteTagHelper

-0.85

ftagPool

-0.84

 intStringLen

-0.83

WebElementEntity

-0.83

 JpaRepository

-0.81

POSITIVE LOGITS

↵

0.45

0.43

0.42

ing

0.40

0.38

My

0.38

’

0.38

Activations Density 0.001%

occurrences of specific programming language syntax or structural elements

special characters or punctuation

No Comments

No Known Activations