INDEX

Explanations

concepts related to biological and medical processes

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

words followed by a related word

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

 Chwiliwch

-0.40

 Domínguez

-0.37

 apaixon

-0.36

 <<<<<<<<<<<<<<

-0.36

 conocía

-0.35

lography

-0.35

pravy

-0.35

 Relaciones

-0.35

 seamlessly

-0.35

 Schäfer

-0.34

POSITIVE LOGITS

 JpaRepository

0.63

 ब्रेकडाउन

0.59

expandindo

0.55

findpost

0.55

tagHelperRunner

0.51

 Olympic

0.51

 ſind

0.50

+#+

0.49

StructEnd

0.49

tonode

0.49

Activations Density 0.229%

concepts related to biological and medical processes

words followed by a related word

No Comments

No Known Activations