INDEX

Explanations

elements and structures related to programming or code syntax

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

object keys and values

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

parsedMessage

-0.70

ScopeManager

-0.60

SequentialGroup

-0.59

GraphicsUnit

-0.59

<unused51>

-0.57

[@BOS@]

-0.56

<unused14>

-0.56

<unused23>

-0.56

<unused8>

-0.56

<unused3>

-0.56

POSITIVE LOGITS

‌

0.47

0.45

0.41

‐

0.40

0.39

0.38

�

0.38

‌‌

0.38

Activations Density 0.427%

elements and structures related to programming or code syntax

object keys and values

No Comments

No Known Activations