INDEX

Explanations

terms related to cytokine measurement and immune response activities

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

cytokine / cytokines

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

 Hager

-0.34

ionView

-0.32

app

-0.32

moveToFirst

-0.31

 placing

-0.31

 anzub

-0.30

 optik

-0.29

 automatic

-0.29

str

-0.29

append

-0.28

POSITIVE LOGITS

tokine

1.01

 cytokines

0.92

 cytokine

0.90

leukin

0.82

 estekak

0.76

 ſever

0.73



0.70

protoimpl

0.66

bootstrapcdn

0.66

 ſta

0.64

Activations Density 0.175%

terms related to cytokine measurement and immune response activities

cytokine / cytokines

No Comments

No Known Activations