INDEX

Explanations

terms related to neuroprotection and immune responses

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

preceding "protection" or forms of "protect."

np_acts-logits-general · gemini-2.0-flash

protection via conferred, offer, provide, shielded, guard

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SuppressLint

-0.50

ⓧ

-0.48

mények

-0.47

 GeoNames

-0.44

estream

-0.42

 lanterna

-0.40

khana

-0.40

้าย

-0.40

jsonPath

-0.39

npos

-0.39

POSITIVE LOGITS

 protection

3.00

protection

2.57

 Protection

2.54

 protect

2.50

 protecting

2.49

Protection

2.45

 protective

2.38

 protections

2.35

 protects

2.34

 PROTECTION

2.32

Activations Density 0.572%

terms related to neuroprotection and immune responses

preceding "protection" or forms of "protect."

protection via conferred, offer, provide, shielded, guard

No Comments

No Known Activations