INDEX

Explanations

terms related to optical and measurement processes

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

preceding properties, areas, or elements

np_acts-logits-general · gemini-2.0-flash

technical measurement terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 OMITBAD

-0.56

vician

-0.52

urlopen

-0.50

principalTable

-0.50

Gigi

-0.46

DeleteBehavior

-0.46

AppCompat

-0.46

__["

-0.45

Према

-0.43

RUnlock

-0.43

POSITIVE LOGITS

VersionUID

0.76

 FetchType

0.66

 BoxDecoration

0.65

новништво

0.64

 gynhyrchwyd

0.63

wikimedia

0.61

 <<<<<<<<<<<<<<

0.61

SPATH

0.59

ParallelGroup

0.58

 endogenous

0.57

Activations Density 1.162%

terms related to optical and measurement processes

preceding properties, areas, or elements

technical measurement terms

No Comments

No Known Activations