INDEX

Explanations

references to the head or hair in a literal or figurative sense

oai_token-act-pair · gemini-2.0-flash

head

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hysema

-0.48

atera

-0.48

 Bacteriol

-0.47

 Cortés

-0.47

Abitanti

-0.45

眼里

-0.45

armi

-0.44

 Bork

-0.43

 Pizarro

-0.43

 Gunnar

-0.43

POSITIVE LOGITS

 head

1.93

 heads

1.73

head

1.69

 Head

1.62

Head

1.58

 HEAD

1.57

heads

1.54

HEAD

1.52

 Heads

1.45

 kepala

1.43

Activations Density 1.577%

references to the head or hair in a literal or figurative sense

head

No Comments

No Known Activations