INDEX

Explanations

terms related to landscapes and natural environments

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

natural environments

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

corpions

-0.43

SENS

-0.42

Http

-0.42

 onscreen

-0.41

Deb

-0.41

 tells

-0.40

Pron

-0.40

whereas

-0.40

ERICAN

-0.40

mbolic

-0.40

POSITIVE LOGITS

 pasture

1.93

 Pasture

1.92

 pastures

1.60

 meadow

0.77

 pasto

0.75

 grassland

0.73

 Meadow

0.65

sidemargin

0.61

 meadows

0.60

 skog

0.60

Activations Density 0.001%

terms related to landscapes and natural environments

natural environments

No Comments

No Known Activations