INDEX

Explanations

structured data formats or object properties

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

code syntax and strings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

GraphicsUnit

-0.58

even

-0.56

 even

-0.56

especially

-0.52

#![

-0.50

 bahkan

-0.48

 حتی

-0.46

 даже

-0.44

 especially

-0.44

 Exactos

-0.44

POSITIVE LOGITS

EDEFAULT

0.50

 referrerpolicy

0.47

Autoritní

0.46

NameInMap

0.45

RenderAtEndOf

0.43

.*")]

0.41

'';

0.39

"]);

0.39

."</

0.39

vejte

0.39

Activations Density 0.029%

structured data formats or object properties

code syntax and strings

No Comments

No Known Activations