INDEX

Explanations

references to mental and physical health practices or guidelines

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

lem, lemma, mathematical notation

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

...

-0.45

...

-0.43

 reflexão

-0.41

 mariposas

-0.40

Referencias

-0.40

 embalagem

-0.40

 interactiva

-0.39

 econômica

-0.38

 chuva

-0.38

 rozwiąz

-0.38

POSITIVE LOGITS

IsMutable

0.88

ſelben

0.80

ftagPool

0.80

 للمعارف

0.79

 ſans

0.77

Efq

0.77

 queſto

0.77

StructEnd

0.76

featureID

0.75

 zwiſchen

0.75

Activations Density 0.012%

references to mental and physical health practices or guidelines

lem, lemma, mathematical notation

No Comments

No Known Activations