INDEX

Explanations

punctuation and formatting elements used in code

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

user input

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

AddTagHelper

-0.93

endphp

-0.85

 CreateTagHelper

-0.83

 Normdatei

-0.82

RegressionTest

-0.82

 disambiguazione

-0.82

httphttps

-0.81

 OMITBAD

-0.79

:✨

-0.77

 doInBackground

-0.76

POSITIVE LOGITS

 cell

0.44

cell

0.42

Cell

0.37

 Cell

0.36

RecyclerView

0.35

cy

0.34

ViewHolder

0.31

law

0.30

property

0.30

row

0.29

Activations Density 0.001%

punctuation and formatting elements used in code

user input

No Comments

No Known Activations