INDEX

Explanations

specific references to gene or protein receptors

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

GH or GHS variants

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

 Leisure

-0.40

 leisure

-0.40

ra

-0.40

Spl

-0.40

bac

-0.39

 Intercept

-0.39

filtration

-0.39

jo

-0.38

kab

-0.37

Tou

-0.36

POSITIVE LOGITS

GHS

3.47

GHS

2.30

ghs

1.16

GH

1.04

GH

1.04

gh

0.82

Gh

0.78

gh

0.77

Gh

0.74

:✨

0.70

Activations Density 0.000%

specific references to gene or protein receptors

GH or GHS variants

No Comments

No Known Activations