INDEX

Explanations

references to scientific studies or data points

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

citations and references

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

 betweenstory

-0.75

delwed

-0.47

 ***/

-0.46

Jeografia

-0.45

tagHelperRunner

-0.42

>');

-0.41

+```

-0.40

unteer

-0.40

httphttps

-0.39

POSITIVE LOGITS

 صوتيه

0.45

AttributeSet

0.44

 Planeten

0.44

 Simplemente

0.43

 hacerlo

0.43

kregen

0.42

 Wünsche

0.42

 AttributeSet

0.41

 GenerationType

0.41

 Spagna

0.41

Activations Density 0.130%

references to scientific studies or data points

citations and references

No Comments

No Known Activations