INDEX

Explanations

the presence and variations of the term "cer" and its related forms

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

"Cer" (often part of "Ceres" or "Cerro")

np_acts-logits-general · gemini-2.0-flash

Cer- prefixed words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

enumii

-0.77

enumi

-0.67

 NSCoder

-0.61

ttino

-0.60

 light

-0.59

GeneratedMessage

-0.56

ритори

-0.56

>{@

-0.56

gdx

-0.56

uckles

-0.55

POSITIVE LOGITS

 Ceres

0.51

WarningLevel

0.50

Cer

0.50

Cer

0.48

cer

0.47

typename

0.46

Ikus

0.46

ker

0.46

olympic

0.45

setCharacter

0.44

Activations Density 0.117%

the presence and variations of the term "cer" and its related forms

"Cer" (often part of "Ceres" or "Cerro")

Cer- prefixed words

No Comments

No Known Activations