INDEX

Explanations

terminology related to immune responses and vaccinations

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

humoral immune response

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

 فريبيس

-0.88

Билгалдахарш

-0.66

 وتسجيلات

-0.63

RTCK

-0.59

 صوتيه

-0.57

-------------</

-0.57

TRAILING

-0.56

 surla

-0.56

 يتيمه

-0.55

 tartalomajánló

-0.54

POSITIVE LOGITS

 antibody

0.45

 immune

0.42

 Immunol

0.41

 immun

0.41

 vaccination

0.40

 immunity

0.38

 antibodies

0.38

phylactic

0.37

 immunization

0.36

 imun

0.36

Activations Density 0.416%

terminology related to immune responses and vaccinations

humoral immune response

No Comments

No Known Activations