INDEX

Explanations

expressions related to personal determination and resilience

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

declarations and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

UnusedPrivate

-0.54

 provavelmente

-0.44

AccessorTable

-0.41

 الرياضيه

-0.40

 découverte

-0.40

 riktigt

-0.39

 terribly

-0.39

 really

-0.39

 gerçekten

-0.39

 auraient

-0.39

POSITIVE LOGITS

 Whoever

0.60

 whoever

0.59

Whoever

0.54

 Whatever

0.52

Whatever

0.52

 READY

0.50

Screw

0.49

 RESIST

0.49

 nobody

0.48

whatever

0.48

Activations Density 0.073%

expressions related to personal determination and resilience

declarations and actions

No Comments

No Known Activations