INDEX

Explanations

declarative statements related to scientific or technical descriptions

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

Code, math, or degree symbols

np_acts-logits-general · gemini-2.0-flash

degree units

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 protoimpl

-0.59

 }^{[

-0.49

subsection

-0.47

 EconPapers

-0.46

jupiter

-0.46

labelledby

-0.45

 pseud

-0.45

}^{+}

-0.45

 Doub

-0.45

siga

-0.44

POSITIVE LOGITS

tanleria

0.70

 propOrder

0.59

MockMvc

0.58

ngdoc

0.58

SupportActionBar

0.57

IUrlHelper

0.56

 Genesee

0.55

encodeWith

0.52

GIVEREF

0.51

 Eminem

0.51

Activations Density 0.059%

declarative statements related to scientific or technical descriptions

Code, math, or degree symbols

degree units

No Comments

No Known Activations