INDEX

Model

gemma-2-9b-it

Layer #

Steering Hook

blocks.20.hook_resid_pre

Steering Strength

Uploader

bot-neuronpedia

Created At

2/15/2025 1:06:43 AM

Raw Vector

Actions

Explanations

No Explanations Found

New Auto-Interp

Configuration

pyvene/gemma-reft-r1-9b-it-res/l20

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pret

-0.38

 commissioning

-0.37

 stabilize

-0.36

-0.35

>')

-0.35

«

-0.34

 virgin

-0.34

 proti

-0.34

mour

-0.34

 IMPRO

-0.33

POSITIVE LOGITS

 myſelf

0.69

ſelf

0.66

PerformLayout

0.63

 phone

0.59

 plufieurs

0.59

ValueStyle

0.59

 ſol

0.57

 propOrder

0.57

 resourceCulture

0.56

 للمعارف

0.56

Activations Density 0.000%

No Comments

No Known Activations