INDEX

Explanations

references to reports or allegations, particularly those involving governmental or organizational activities

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

reporting facts or suspicions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

LEGGI

-0.41

 utafitiHapana

-0.40

 resourceCulture

-0.40

."\

-0.40

Šaltiniai

-0.39

 scienza

-0.38

+#+#

-0.38

Pozri

-0.38

kitan

-0.38

 LETTERS

-0.38

POSITIVE LOGITS

 eyewitness

0.49

 witness

0.47

 witnesses

0.47

ValueGeneration

0.46

 witnessed

0.45

EndContext

0.43

reuters

0.41

 Witness

0.40

 testemun

0.40

被害

0.39

Activations Density 0.040%

references to reports or allegations, particularly those involving governmental or organizational activities

reporting facts or suspicions

No Comments

No Known Activations