INDEX

Explanations

various forms of scale and measurements in a technical context

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

scale bar

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

tanleria

-0.56

 يتيمه

-0.55

 Wikimedijinoj

-0.55

 Population

-0.54

 Partici

-0.54

 ControllerBase

-0.54

WebElementEntity

-0.52

RRect

-0.51

 resourceCulture

-0.50

 otomatig

-0.50

POSITIVE LOGITS

 scale

1.88

scale

1.75

Scale

1.71

 Scale

1.70

 SCALE

1.59

 scales

1.52

SCALE

1.47

 escala

1.42

 scaling

1.38

scales

1.35

Activations Density 0.047%

various forms of scale and measurements in a technical context

scale bar

No Comments

No Known Activations

various forms of scale and measurements in a technical context

scale bar

No Comments

No Known Activations