INDEX

Explanations

medical terminology related to patient conditions and evaluations

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

percentages of patients

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

 starfish

-0.47

Ul

-0.47

 vinaigrette

-0.45

 pinulongan

-0.43

Bounds

-0.43

IRB

-0.43

Fin

-0.43

 Oval

-0.42

Lof

-0.41

neuron

-0.41

POSITIVE LOGITS

RegressionTest

0.54

WithIOException

0.46

RuleContext

0.45

RTHOOK

0.43

zzleHttp

0.41

PreferredItem

0.41

BufferException

0.40

 havde

0.40

yntaxException

0.40

 externi

0.40

Activations Density 0.406%

medical terminology related to patient conditions and evaluations

percentages of patients

No Comments

No Known Activations