INDEX

Explanations

key terms related to specific scientific or technical processes and equipment configurations

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

Angle brackets containing text

np_acts-logits-general · gemini-2.0-flash

technical terms after punctuation

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nahilalakip

-0.54

CppCodeGen

-0.49

RenderAtEndOf

-0.46

égard

-0.46

MVH

-0.44

advised

-0.42

extAlignment

-0.42

ⓧ

-0.42

 propOrder

-0.42

Jîn

-0.41

POSITIVE LOGITS

ScopeManager

0.43

Dedicated

0.37

*********/

0.34

enderror

0.34

protoimpl

0.34

 jsPsych

0.33

 EconPapers

0.33

 CascadeType

0.33

chyma

0.33

="/">

0.32

Activations Density 1.078%

key terms related to specific scientific or technical processes and equipment configurations

Angle brackets containing text

technical terms after punctuation

No Comments

No Known Activations