INDEX

Explanations

terms related to experimental procedures and quantifiable results in scientific studies

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

scale bars and magnifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 المعيارى

-0.60

 يتيمه

-0.58

 monoclonal

-0.56

 antibody

-0.54

 Antibodies

-0.54

matchCondition

-0.52

 antibodies

-0.52

plotlib

-0.51

 виправивши

-0.50

WebServlet

-0.50

POSITIVE LOGITS

bar

0.41

Scale

0.38

scale

0.37

сшта

0.37

bar

0.37

 Magna

0.35

 بس

0.35

 bars

0.34

count

0.33

 WORTH

0.33

Activations Density 0.280%

terms related to experimental procedures and quantifiable results in scientific studies

scale bars and magnifications

No Comments

No Known Activations