INDEX

Explanations

numerical data and measurements related to scientific or technical contexts

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

numbers and units

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

matchCondition

-0.64

 ProtoMessage

-0.58

ScopeManager

-0.50

principalTable

-0.48

 CreateTagHelper

-0.47

 harmonious

-0.47

 Bioaccumulative

-0.47

orianCalendar

-0.45

\{\\

-0.44

 harmonize

-0.44

POSITIVE LOGITS

 preghiera

0.46

 pioggia

0.43

didSet

0.39

mögens

0.39

 kautta

0.39

 äta

0.38

 ditambah

0.38

 ympä

0.38

 låg

0.36

 helft

0.35

Activations Density 0.147%

numerical data and measurements related to scientific or technical contexts

numbers and units

No Comments

No Known Activations