INDEX

Explanations

terms related to biological and pharmacological concepts

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

scientific and biological processes

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

GOTREF

-0.66

новниш

-0.62

OCCURRED

-0.54

tahui

-0.52

 HasFactory

-0.51

RegressionTest

-0.51

Geplaatst

-0.50

 ſeine

-0.49

 ſeiner

-0.48

 autorytatywna

-0.48

POSITIVE LOGITS

ViewFeatures

0.52

цездатний

0.51

 ब्रेकडाउन

0.50

 Италијани

0.39

物

0.38

 always

0.37

 contextLoads

0.36

 generally

0.35

sempre

0.35

 Always

0.33

Activations Density 0.260%

terms related to biological and pharmacological concepts

scientific and biological processes

No Comments

No Known Activations