INDEX

Explanations

JSON object structures

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

user or code snippets

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

-0.42

苯

-0.42

<bos>

-0.40

 Miller

-0.35

 know

-0.34

 дове

-0.33

 anla

-0.32

 bear

-0.32

 रूप

-0.32

POSITIVE LOGITS

:{

1.88

":{

1.34

:{

1.30

:{

1.27

':{

1.16

:[

1.09

':{'

1.07

":{"

1.00

:['

0.96

:${

0.95

Activations Density 0.009%

JSON object structures

user or code snippets

No Comments

No Known Activations