INDEX

Explanations

blocks of code or programming syntax

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

C++ and Python 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

Personendaten

-0.71

ⓧ

-0.67

tanleria

-0.59

 Púb

-0.58

setVerticalGroup

-0.54

 dezelve

-0.53

 lèvres

-0.53

 zijne

-0.53

SequentialGroup

-0.51

POSITIVE LOGITS

ंदीखरीदारी

0.34

InitVars

0.33

 Fonda

0.33

 babi

0.33

 initiatives

0.33

Zil

0.33

ầu

0.32

ella

0.31

دانشنامهٔ

0.31

tritt

0.31

Activations Density 0.009%

blocks of code or programming syntax

C++ and Python code snippets

No Comments

No Known Activations