INDEX

Explanations

CSS style attributes and layout specifications

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

user input classifier

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

AxisAlignment

-0.74

BagLayout

-0.66

 MainAxisSize

-0.66

SequentialGroup

-0.64

 BoxFit

-0.60

BagConstraints

-0.54

 FontWeight

-0.54

ɵɵelementStart

-0.54

 createSprite

-0.54

jspb

-0.54

POSITIVE LOGITS

Дереккөздер

0.36

 NSCoder

0.33

nextProps

0.33

มาย

0.31

 față

0.31

][:

0.30

''}

0.29

 interp

0.29

 verdad

0.29

rimid

0.29

Activations Density 0.080%

CSS style attributes and layout specifications

user input classifier

No Comments

No Known Activations