INDEX

Explanations

military operations and missions

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

operation or project names

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

RTLR

-0.42

 vechi

-0.39

 segno

-0.38

assemblée

-0.38

attente

-0.38

adhé

-0.38

 fehlt

-0.37

interprétation

-0.37

GEBURTS

-0.37

queles

-0.37

POSITIVE LOGITS

 intptr

0.62

 Operation

0.57

RTEE

0.56

GenerationType

0.54

__':

0.52

 bezeichneter

0.52

Operation

0.51

Sucesor

0.51

 Operations

0.50

NewGuid

0.50

Activations Density 0.021%

military operations and missions

operation or project names

No Comments

No Known Activations