INDEX

Explanations

scientific terms related to thermal analysis

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

TGA and mass loss

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 Autorisations

-0.52

 Réalisation

-0.52

IntoConstraints

-0.50

 Exacts

-0.49

ortunadamente

-0.48



-0.47

 gouverneur

-0.47

 ſoll

-0.47

 prêtre

-0.47

stickers

-0.47

POSITIVE LOGITS

ang

0.38

Autoritní

0.34

heiz

0.33

amate

0.32

 onStart

0.32

cio

0.32

MockMvc

0.31

 loss

0.31

def

0.30

loss

0.30

Activations Density 0.198%

scientific terms related to thermal analysis

TGA and mass loss

No Comments

No Known Activations