INDEX

Explanations

references to television networks and their programming

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

international television channels

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

WithIOException

-0.44

Shel

-0.44

OLEAN

-0.40

Scatter

-0.40

Diweddarwch

-0.40

Scul

-0.39

 snippetHide

-0.39

⅘

-0.38

 Maestro

-0.38

NYC

-0.38

POSITIVE LOGITS

 Globo

0.59

RTL

0.51

TV

0.51

globo

0.49

TV

0.49

NRK

0.46

 defaultstate

0.46

 globo

0.46

lusconi

0.45

 television

0.44

Activations Density 0.019%

references to television networks and their programming

international television channels

No Comments

No Known Activations