INDEX

Explanations

references to software functionalities and features

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

Follows UI editing/coding terms

np_acts-logits-general · gemini-2.0-flash

layer or layers

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

LookAnd

-0.91

contentLoaded

-0.71

 financed

-0.67

 AssemblyTitle

-0.64

@[+][

-0.63

gameserver

-0.63

httphttps

-0.62

 CreateTagHelper

-0.62

Portale

-0.62

 समीक्षक

-0.60

POSITIVE LOGITS

 layers

0.90

 layer

0.88

 Layer

0.84

 Layers

0.81

Layers

0.73

Layer

0.71

 LAYER

0.70

layers

0.67

layer

0.67

 tool

0.63

Activations Density 0.259%

references to software functionalities and features

Follows UI editing/coding terms

layer or layers

No Comments

No Known Activations