INDEX

Explanations

mathematical symbols and expressions related to algebraic structures

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

projective space notation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

AddTagHelper

-0.77

 kaarangay

-0.63

balleur

-0.57

 للمعارف

-0.57

хьтан

-0.56

 Autorizaciones

-0.56

EDEFAULT

-0.55

Tikang

-0.54

WriteBarrier

-0.54

kháu

-0.52

POSITIVE LOGITS

msub

0.78

msubsup

0.61

 nivelul

0.45

msup

0.44

 mistrzost

0.40

‘

0.39

ed

0.39

quele

0.39

 Nagel

0.39

${{

0.39

Activations Density 0.090%

mathematical symbols and expressions related to algebraic structures

projective space notation

No Comments

No Known Activations