INDEX

Explanations

technical terms related to programming and web development

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

routing

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

TypedDataSet

-0.50

__':

-0.48

__":

-0.47

/*!

-0.44

BASEPATH

-0.44

findpost

-0.43

 poffible

-0.42

AddTagHelper

-0.40

gamesh

-0.40

*************/

-0.40

POSITIVE LOGITS

routing

2.69

 routing

1.66

 Routing

1.48

Routing

1.20

 routed

1.05

routed

1.03

ROUT

1.02

 route

0.98

route

0.94

 ROUT

0.94

Activations Density 0.000%

technical terms related to programming and web development

routing

No Comments

No Known Activations