INDEX

Explanations

technical terms related to printing and design

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

linotype and matrices

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

 CreateTagHelper

-0.57

WriteTagHelper

-0.51

MemoryWarning

-0.44

 AssemblyTitle

-0.43

RTSC

-0.43

 ब्रेकडाउन

-0.42

 برانيه

-0.42

 pronunciation

-0.42

 kaarangay

-0.40

addPreferredGap

-0.38

POSITIVE LOGITS

rungsseite

0.57

 Autorisations

0.45

ftagPool

0.44

CardContent

0.44

NECTION

0.43

AutoScaleMode

0.41

 pasaje

0.40

 Straße

0.40

matrix

0.40

Sims

0.40

Activations Density 0.097%

technical terms related to printing and design

linotype and matrices

No Comments

No Known Activations