INDEX

Explanations

technical tutorials and procedural texts

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

time durations

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

+#+

-0.59

 kasarigan

-0.56

rungsseite

-0.52

ainville

-0.51

principalTable

-0.50

########.

-0.48

oa̍t

-0.46



-0.45

angliski

-0.44

EDEFAULT

-0.44

POSITIVE LOGITS

 minutes

0.90

 minute

0.81

 seconds

0.79

 Minutes

0.78

minutes

0.77

 minutos

0.77

Minutes

0.74

 MINUTES

0.74

 minuto

0.73

 минут

0.71

Activations Density 0.103%

technical tutorials and procedural texts

time durations

No Comments

No Known Activations