INDEX

Explanations

terms related to coding and programming concepts

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

imported libraries or templates

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

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

 esclavos

-0.45

MessageOf

-0.43

 Moscú

-0.43

 empleos

-0.42

 penjara

-0.41

 neumáticos

-0.40

corazón

-0.38

 conclusiones

-0.38

 explotación

-0.38

 sendok

-0.38

POSITIVE LOGITS

tpl

1.68

tpl

1.05

 autorytatywna

0.84

TPL

0.82

Tpl

0.80

smarty

0.70

ScopeManager

0.69

 模板

0.66

migrationBuilder

0.66

 template

0.66

Activations Density 0.000%

terms related to coding and programming concepts

imported libraries or templates

No Comments

No Known Activations