INDEX

Explanations

instances of strong positive statements or affirmations

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

code and technical terms

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

This neuron is inactive on the provided data and does not detect any consistent feature (it finds nothing).

oai_token-act-pair · gpt-5-mini Triggered by @vetterc0

standalone decimal numbers (floating-point values) appearing as isolated numeric tokens.

oai_token-act-pair · gpt-5 Triggered by @vetterc0

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

 bahía

-0.52

 artesanía

-0.43

 cuarzo

-0.42

 jaula

-0.41

 duración

-0.39

 kuiten

-0.38

 algodón

-0.38

guiente

-0.38

 odeur

-0.38

 aguja

-0.38

POSITIVE LOGITS

 MainAxisSize

0.63

.*")]

0.63

 XNUMX

0.59

'},

0.57

FXML

0.56

PYX

0.55

"},

0.55

MultipartFile

0.55

"");

0.55

')}}

0.54

Activations Density 0.000%

instances of strong positive statements or affirmations

code and technical terms

This neuron is inactive on the provided data and does not detect any consistent feature (it finds nothing).

standalone decimal numbers (floating-point values) appearing as isolated numeric tokens.

No Comments

No Known Activations

instances of strong positive statements or affirmations

code and technical terms

This neuron is inactive on the provided data and does not detect any consistent feature (it finds nothing).

standalone decimal numbers (floating-point values) appearing as isolated numeric tokens.

No Comments

No Known Activations