INDEX

Explanations

This neuron seems to be firing on personal pronouns, conjunctions, and present tense verbs, suggesting it's identifying basic sentence structure and personal narratives across multiple languages (French, Spanish, English, Italian).

oai_token-act-pair · gemini-2.0-flash

state of being

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

SpringBootTest

-0.82

 ddelweddau

-0.81

InitVars

-0.75

berdayakan

-0.74

 Audiodateien

-0.74

 Wikispecies

-0.73

----</

-0.69



-0.68

^(@)

-0.67

 Administrativna

-0.66

POSITIVE LOGITS

 alive

0.62

 intact

0.62

 ablaze

0.57

 underway

0.56

off

0.55

 ahead

0.52

 awake

0.49

 into

0.48

 afloat

0.47

 aside

0.45

Activations Density 6.772%

This neuron seems to be firing on personal pronouns, conjunctions, and present tense verbs, suggesting it's identifying basic sentence structure and personal narratives across multiple languages (French, Spanish, English, Italian).

state of being

No Comments

No Known Activations

This neuron seems to be firing on personal pronouns, conjunctions, and present tense verbs, suggesting it's identifying basic sentence structure and personal narratives across multiple languages (French, Spanish, English, Italian).

state of being

No Comments

No Known Activations