INDEX

Explanations

references to gene-related topics and planning elements in a structured context

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

annotated genes and reference numerals

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 propOrder

-0.61

цездатний

-0.59

saraba

-0.59

InSection

-0.52

 oprot

-0.52

Бахар

-0.51

 wireType

-0.51

__":

-0.50

 OnTrigger

-0.50

ArgsConstructor

-0.49

POSITIVE LOGITS

 незавершена

0.50

 bolsillos

0.43

Jeografia

0.40

kiewicz

0.40

 hornear

0.40

 statement

0.40

 record

0.40

 records

0.39

 precedenti

0.39

 návr

0.39

Activations Density 0.266%

references to gene-related topics and planning elements in a structured context

annotated genes and reference numerals

No Comments

No Known Activations