INDEX

Explanations

numerical values associated with configurations or settings

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

line changes and offsets

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

twimg

-0.54

stdc

-0.52

RenderAtEndOf

-0.52

 Infórmanos

-0.49

 nahilalakip

-0.48

":[{

-0.47

SourceChecksum

-0.47

 برانيه

-0.46

 utafitiHapana

-0.46

abund

-0.45

POSITIVE LOGITS

 Offset

0.53

 offset

0.50

endphp

0.47

Offset

0.42

offset

0.40

numerusform

0.39

StoredProcedure

0.38

对应

0.36

 delayed

0.35

ToHex

0.35

Activations Density 0.059%

numerical values associated with configurations or settings

line changes and offsets

No Comments

No Known Activations