INDEX

Model

gemma-2-9b-it

Layer #

Steering Hook

blocks.20.hook_resid_pre

Steering Strength

52.25

Uploader

bot-neuronpedia

Created At

2/15/2025 1:06:43 AM

Raw Vector

Actions

Explanations

certain types of structured text or code snippets, particularly incorporating punctuation and tags

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 recognised

-0.39

lastonbury

-0.36

rousel

-0.34

 switch

-0.34

 Picchu

-0.34

 renown

-0.33

ndale

-0.33

 batter

-0.33

 Songtext

-0.33

 supersonic

-0.33

POSITIVE LOGITS

 kasarigan

0.55

 ainfi

0.54

Manbalar

0.52

+#+#

0.51

 purpoſe

0.50

 queſta

0.50

ViewInit

0.49

problemas

0.49

Pautan

0.49

 feroit

0.49

Activations Density 0.090%

certain types of structured text or code snippets, particularly incorporating punctuation and tags

No Comments

No Known Activations