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

unique punctuation marks and structure in sentences

oai_token-act-pair · gpt-4o-mini

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

 nawr

-0.40

isième

-0.32

 switch

-0.32

letzt

-0.32

 fertiliser

-0.31

 adulte

-0.29

дыду

-0.29

 recognised

-0.29

ndale

-0.28

 frein

-0.28

POSITIVE LOGITS

 propOrder

0.71

LookAnd

0.69

 насељу

0.64

fromnode

0.63

 Infórmanos

0.61

 שוליים

0.58

LEGGI

0.58

+#+#

0.58

 Италијани

0.56

bibfield

0.55

Activations Density 1.496%

unique punctuation marks and structure in sentences

No Comments

No Known Activations