INDEX

Explanations

scientific terms related to biological activities and extract effects

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

Results or findings in scientific studies

np_acts-logits-general · gemini-2.0-flash

plant extract research results

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

Explicación

-0.74

راط

-0.64

DNEY

-0.63

ագրություններ

-0.62

eneuve

-0.61

LUN

-0.60

يكب

-0.59

fficio

-0.59

<?

-0.59

mazoo

-0.59

POSITIVE LOGITS

SourceChecksum

0.64

˃

0.62

antaranya

0.60

˂

0.58

showed

0.54



0.54

 studied

0.54

GenerationType

0.53

 investigated

0.52

viz

0.52

Activations Density 1.735%

scientific terms related to biological activities and extract effects

Results or findings in scientific studies

plant extract research results

No Comments

No Known Activations