INDEX

Explanations

numerical expressions and mathematical operations

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

negative numbers or values

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

 فريبيس

-0.45

 TextInputType

-0.42

 pulver

-0.39

ufen

-0.38

 assume

-0.38

 assumed

-0.38

ellido

-0.38

 препратки

-0.38

offrir

-0.38

 saites

-0.38

POSITIVE LOGITS

 negative

0.62

Negative

0.59

 Negative

0.56

 negativo

0.55

 négatif

0.54

NEGATIVE

0.52

negative

0.52

 negativ

0.52

fromnode

0.49

 negativos

0.49

Activations Density 0.562%

numerical expressions and mathematical operations

negative numbers or values

No Comments

No Known Activations