INDEX

Explanations

references to legal case citations and reports

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

Cal. Rptr. followed by P.2d

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

cerol

-0.52

 Pati

-0.39

ie

-0.38

hã

-0.37

Pati

-0.36

altro

-0.35

khar

-0.34

ALTERN

-0.34

IMPORTED

-0.34

 Capt

-0.34

POSITIVE LOGITS

Autoritní

0.98

ChildScrollView

0.72

rrggbb

0.63

GEBURTSDATUM

0.60

 indígen

0.58

 ModelRenderer

0.58

 '\\;'

0.54

 AssemblyTitle

0.54

ToBounds

0.52

 estadounid

0.52

Activations Density 0.002%

references to legal case citations and reports

Cal. Rptr. followed by P.2d

No Comments

No Known Activations